National Instruments IMAQ Vision for LabWindows TM CVI User Manual

Download

IMAQ

IMAQ Vision

for LabWindows User Manual

IMAQ Vision for LabWindows/CVI User Manual

/CVITM

August 2004 Edition

Part Number 371266A-01

Support

Worldwide Technical Support and Product Information

ni.com

National Instruments Corporate Headquarters

11500 North Mopac Expressway Austin, Texas 78759-3504 USA Tel: 512 683 0100

Worldwide Offices

Australia 1800 300 800, Austria 43 0 662 45 79 90 0, Belgium 32 0 2 757 00 20, Brazil 55 11 3262 3599, Canada (Calgary) 403 274 9391, Canada (Ottawa) 613 233 5949, Canada (Québec) 450 510 3055, Canada (Toronto) 905 785 0085, Canada (Vancouver) 604 685 7530, China 86 21 6555 7838, Czech Republic 420 224 235 774, Denmark 45 45 76 26 00, Finland 385 0 9 725 725 11, France 33 0 1 48 14 24 24, Germany 49 0 89 741 31 30, India 91 80 51190000, Israel 972 0 3 6393737, Italy 39 02 413091, Japan 81 3 5472 2970, Korea 82 02 3451 3400, Malaysia 603 9131 0918, Mexico 01 800 010 0793, Netherlands 31 0 348 433 466, New Zealand 0800 553 322, Norway 47 0 66 90 76 60, Poland 48 22 3390150, Portugal 351 210 311 210, Russia 7 095 783 68 51, Singapore 65 6226 5886, Slovenia 386 3 425 4200, South Africa 27 0 11 805 8197, Spain 34 91 640 0085, Sweden 46 0 8 587 895 00, Switzerland 41 56 200 51 51, Taiwan 886 2 2528 7227, Thailand 662 992 7519, United Kingdom 44 0 1635 523545

For further support information, refer to the Technical Support and Professional Services appendix. To comment on National Instruments documentation, refer to the National Instruments Web site at ni.com/info and enter the info code feedback.

Important Information

Warranty

The media on which you receive National Instruments software are warranted not to fail to execute programming instructions, due to defects in materials and workmanship, for a period of 90 days from date of shipment, as evidenced by receipts or other documentation. National Instruments will, at its option, repair or replace software media that do not execute programming instructions if National Instruments receives notice of such defects during the warranty period. National Instruments does not warrant that the operation of the software shall be uninterrupted or error free.

A Return Material Authorization (RMA) number must be obtained from the factory and clearly marked on the outside of the package before any equipment will be accepted for warranty work. National Instruments will pay the shipping costs of returning to the owner parts which are covered by warranty.

National Instruments believes that the information in this document is accurate. The document has been carefully reviewed for technical accuracy. In the event that technical or typographical errors exist, National Instruments reserves the right to make changes to subsequent editions of this document without prior notice to holders of this edition. The reader should consult National Instruments if errors are suspected. In no event shall National Instruments be liable for any damages arising out of or related to this document or the information contained in it.

XCEPT AS SPECIFIED HEREIN, NATIONAL INSTRUMENTS MAKES NO WARRANTIES, EXPRESS OR IMPLIED, AND SPECIFICALLY DISCLAIMS ANY WAR RANTY OF

MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE . CUSTOMER’S RIGHT TO RECOVER DAMAGES CAUSED BY FAULT OR NEGLIGENCE ON THE PART OF

ATIONAL INSTRUMENTS SHALL BE LIMITED TO THE AMOUNT THERETOFORE PAID BY THE CUSTOMER. NATIONAL INSTRUMENTS WILL NOT BE LIABLE FOR DAMAGES RESULTING FROM LOSS OF DATA, PROFITS, USE OF PRODUCTS, OR INCIDENTAL OR CONSEQUENTIAL DAMAGES, EVEN IF ADVISED OF THE POSS IBILITY THEREOF. This limitation of the liability of National Instruments will apply regardless of the form of action, whether in contract or tort, including

negligence. Any action against National Instruments must be brought within one year after the cause of action accrues. National Instruments shall not be liable for any delay in performance due to causes beyond its reasonable control. The warranty provided herein does not cover damages, defects, malfunctions, or service failures caused by owner’s failure to follow the National Instruments installation, operation, or maintenance instructions; owner’s modification of the product; owner’s abuse, misuse, or negligent acts; and power failure or surges, fire, flood, accident, actions of third parties, or other events outside reasonable control.

Copyright

Under the copyright laws, this publication may not be reproduced or transmitted in any form, electronic or mechanical, including photocopying, recording, storing in an information retrieval system, or translating, in whole or in part, without the prior written consent of National Instruments Corporation.

Trademarks

CVI™, IMAQ™, LabVIEW™, National Instruments™, National Instruments Alliance Partner™, NI™, ni.com™, NI Developer Zone™, and NI-IMAQ

Product and company names mentioned herein are trademarks or trade names of their respective companies.

Members of the National Instruments Alliance Partner Program are business entities independent from National Instruments and have no agency, partnership, or joint-venture relationship with National Instruments.

™

are trademarks of National Instruments Corporation.

Patents

For patents covering National Instruments products, refer to the appropriate location: Help»Patents in your software, the patents.txt file on your CD, or

ni.com/patents.

WARNING REGARDING USE OF NATIONAL INSTRUMENTS PRODUCTS

(1) NATIONAL INSTRUMENTS PRODUCTS ARE NOT DESIGNED WITH COMPONENTS AND TESTING FOR A LEVEL OF RELIABILITY SUITABLE FOR USE IN OR IN CONNECTION WITH SURGICAL IMPLANTS OR AS CRITICAL COMPONENTS IN ANY LIFE SUPPORT SYSTEMS WHOSE FAILURE TO PERFORM CAN REASONABLY BE EXPECTED TO CAUSE SIGNIFICANT INJURY TO A HUMAN.

(2) IN ANY APPLICATION, INCLUDING THE ABOVE, RELIABILITY OF OPERATION OF THE SOFTWARE PRODUCTS CAN BE IMPAIRED BY ADVERSE FACTORS, INCLUDING BUT NOT LIMITED TO FLUCTUATIONS IN ELECTRICAL POWER SUPPLY, COMPUTER HARDWARE MALFUNCTIONS, COMPUTER OPERATING SYSTEM SOFTWARE FITNESS, FITNESS OF COMPILERS AND DEVELOPMENT SOFTWARE USED TO DEVELOP AN APPLICATION, INSTALLATION ERRORS, SOFTWARE AND HARDWARE COMPATIBILITY PROBLEMS, MALFUNCTIONS OR FAILURES OF ELECTRONIC MONITORING OR CONTROL DEVICES, TRANSIENT FAILURES OF ELECTRONIC SYSTEMS (HARDWARE AND/OR SOFTWARE), UNANTICIPATED USES OR MISUSES, OR ERRORS ON THE PART OF THE USER OR APPLICATIONS DESIGNER (ADVERSE FACTORS SUCH AS THESE ARE HEREAFTER COLLECTIVELY TERMED “SYSTEM FAILURES”). ANY APPLICATION WHERE A SYSTEM FAILURE WOULD CREATE A RISK OF HARM TO PROPERTY OR PERSONS (INCLUDING THE RISK OF BODILY INJURY AND DEATH) SHOULD NOT BE RELIANT SOLELY UPON ONE FORM OF ELECTRONIC SYSTEM DUE TO THE RISK OF SYSTEM FAILURE. TO AVOID DAMAGE, INJURY, OR DEATH, THE USER OR APPLICATION DESIGNER MUST TAKE REASONABLY PRUDENT STEPS TO PROTECT AGAINST SYSTEM FAILURES, INCLUDING BUT NOT LIMITED TO BACK-UP OR SHUT DOWN MECHANISMS. BECAUSE EACH END-USER SYSTEM IS CUSTOMIZED AND DIFFERS FROM NATIONAL INSTRUMENTS' TESTING PLATFORMS AND BECAUSE A USER OR APPLICATION DESIGNER MAY USE NATIONAL INSTRUMENTS PRODUCTS IN COMBINATION WITH OTHER PRODUCTS IN A MANNER NOT EVALUATED OR CONTEMPLATED BY NATIONAL INSTRUMENTS, THE USER OR APPLICATION DESIGNER IS ULTIMATELY RESPONSIBLE FOR VERIFYING AND VALIDATING THE SUITABILITY OF NATIONAL INSTRUMENTS PRODUCTS WHENEVER NATIONAL INSTRUMENTS PRODUCTS ARE INCORPORATED IN A SYSTEM OR APPLICATION, INCLUDING, WITHOUT LIMITATION, THE APPROPRIATE DESIGN, PROCESS AND SAFETY LEVEL OF SUCH SYSTEM OR APPLICATION.

About This Manual

Conventions ...................................................................................................................ix

Related Documentation..................................................................................................x

IMAQ Vision...................................................................................................x

NI Vision Assistant..........................................................................................x

NI Vision Builder for Automated Inspection ..................................................x

Other Documentation ......................................................................................xi

Chapter 1 Introduction to IMAQ Vision

About IMAQ Vision ......................................................................................................1-1

Application Development Environments.......................................................................1-1

IMAQ Vision Function Tree..........................................................................................1-2

IMAQ Machine Vision Function Tree...........................................................................1-3

Creating IMAQ Vision Applications.............................................................................1-4

Chapter 2 Getting Measurement-Ready Images

Set Up Your Imaging System ........................................................................................2-1

Calibrate Your Imaging System ....................................................................................2-2

Create an Image .............................................................................................................2-2

Source and Destination Images .......................................................................2-4

Acquire or Read an Image .............................................................................................2-5

Acquiring an Image .........................................................................................2-6

Reading a File..................................................................................................2-6

Converting an Array to an Image ....................................................................2-7

Display an Image ...........................................................................................................2-7

Attach Calibration Information......................................................................................2-8

Analyze an Image ..........................................................................................................2-8

Improve an Image ..........................................................................................................2-9

Lookup Tables .................................................................................................2-10

Filters...............................................................................................................2-10

Convolution Filter .............................................................................2-11

Nth Order Filter.................................................................................2-11

Grayscale Morphology ....................................................................................2-11

FFT ..................................................................................................................2-12

Complex Image Operations ..............................................................2-13

Contents

Chapter 3 Making Grayscale and Color Measurements

Define Regions of Interest............................................................................................. 3-1

Defining Regions Interactively ....................................................................... 3-1

Tools Palette Transformation ........................................................... 3-5

Defining Regions Programmatically............................................................... 3-6

Defining Regions with Masks......................................................................... 3-6

Measure Grayscale Statistics......................................................................................... 3-7

Measure Color Statistics................................................................................................ 3-7

Comparing Colors ........................................................................................... 3-9

Learning Color Information ............................................................................ 3-9

Specifying the Color Information to Learn ...................................... 3-9

Choosing a Color Representation Sensitivity ................................... 3-12

Ignoring Learned Colors................................................................... 3-13

Chapter 4 Performing Particle Analysis

Create a Binary Image ................................................................................................... 4-1

Improve the Binary Image............................................................................................. 4-2

Removing Unwanted Particles........................................................................ 4-3

Separating Touching Particles ........................................................................ 4-3

Improving Particle Shapes .............................................................................. 4-3

Make Particle Measurements ........................................................................................ 4-4

Chapter 5 Performing Machine Vision Tasks

Locate Objects to Inspect .............................................................................................. 5-2

Using Edge Detection to Build a Coordinate Transform ................................ 5-4

Using Pattern Matching to Build a Coordinate Transform .............................5-6

Choosing a Method to Build the Coordinate Transform................................. 5-7

Set Search Areas............................................................................................................ 5-8

Defining Regions Interactively ....................................................................... 5-8

Defining Regions Programmatically............................................................... 5-9

Find Measurement Points .............................................................................................. 5-9

Finding Features Using Edge Detection ......................................................... 5-9

Finding Lines or Circles ................................................................... 5-10

Finding Edge Points Along One Search Contour ............................. 5-11

Finding Edge Points Along Multiple Search Contours ....................5-12

Finding Points Using Pattern Matching.......................................................... 5-13

Defining and Creating Good Template Images ................................ 5-13

Training the Pattern Matching Algorithm ........................................ 5-15

IMAQ Vision for LabWindows/CVI User Manual vi ni.com

Contents

Defining a Search Area .....................................................................5-16

Setting Matching Parameters and Tolerances...................................5-17

Testing the Search Algorithm on Test Images..................................5-18

Using a Ranking Method to Verify Results ......................................5-19

Finding Points Using Color Pattern Matching ................................................5-19

Defining and Creating Good Color Template Images ......................5-20

Training the Color Pattern Matching Algorithm...............................5-21

Defining a Search Area .....................................................................5-22

Setting Matching Parameters and Tolerances...................................5-23

Testing the Search Algorithm on Test Images..................................5-25

Finding Points Using Color Location..............................................................5-25

Convert Pixel Coordinates to Real-World Coordinates.................................................5-26

Make Measurements ......................................................................................................5-26

Distance Measurements...................................................................................5-26

Analytic Geometry Measurements ..................................................................5-27

Instrument Reader Measurements ...................................................................5-27

Identify Parts Under Inspection .....................................................................................5-28

Classifying Samples ........................................................................................5-28

Reading Characters..........................................................................................5-29

Reading Barcodes............................................................................................5-30

Reading 1D Barcodes........................................................................5-30

Reading Data Matrix Barcodes .........................................................5-30

Reading PDF417 Barcodes ...............................................................5-31

Display Results ..............................................................................................................5-31

Chapter 6 Calibrating Images

Perspective and Nonlinear Distortion Calibration .........................................................6-1

Defining a Calibration Template.....................................................................6-2

Defining a Reference Coordinate System .......................................................6-3

Learning Calibration Information....................................................................6-5

Specifying Scaling Factors................................................................6-6

Choosing a Region of Interest...........................................................6-6

Choosing a Learning Algorithm .......................................................6-6

Using the Learning Score..................................................................6-7

Learning the Error Map.....................................................................6-8

Learning the Correction Table ..........................................................6-8

Setting the Scaling Method ...............................................................6-8

Calibration Invalidation ....................................................................6-8

Simple Calibration .........................................................................................................6-9

Save Calibration Information.........................................................................................6-10

Attach Calibration Information......................................................................................6-10

Contents

Appendix A Technical Support and Professional Services

Glossary

Index

IMAQ Vision for LabWindows/CVI User Manual viii ni.com

About This Manual

The IMAQ Vision for LabWindows/CVI User Manual is intended for

engineers and scientists who have knowledge of the LabWindows

programming environment and need to create machine vision and image

processing applications using C functions. The manual guides you through

tasks beginning with setting up your imaging system to taking

measurements.

™

/CVI™

Conventions

The following conventions are used in this manual:

» The » symbol leads you through nested menu items and dialog box options

to a final action. The sequence File»Page Setup»Options directs you to

pull down the File menu, select the Page Setup item, and select Options

from the last dialog box.

This icon denotes a tip, which alerts you to advisory information.

This icon denotes a note, which alerts you to important information.

bold Bold text denotes items that you must select or click in the software, such

as menu items and dialog box options. Bold text also denotes parameter

names.

italic Italic text denotes variables, emphasis, a cross reference, or an introduction

to a key concept. This font also denotes text that is a placeholder for a word

or value that you must supply.

monospace Text in this font denotes text or characters that you should enter from the

keyboard, sections of code, programming examples, and syntax examples.

This font is also used for the proper names of disk drives, paths, directories,

programs, subprograms, subroutines, device names, functions, operations,

variables, filenames, and extensions.

About This Manual

management.

Functions that create and manipulate regions of interest.

Functions that compute the centroid of an image, profile of a line of pixels, and the mean line profile. This type also includes functions that calculate the pixel distribution and statistical parameters of an image.

Functions for grayscale image processing and analysis.

Binary Processing

Color Processing

Pattern Matching

IMAQ Vision for LabWindows/CVI User Manual 1-2 ni.com

Functions for binary image processing and analysis.

Functions for color image processing and analysis.

Functions that learn patterns and search for patterns in images.

Chapter 1 Introduction to IMAQ Vision

Table 1-1. IMAQ Vision Function Types (Continued)

Function Type Description

Caliper Functions designed for gauging, measurement, and inspection applications.

Operators Functions that perform arithmetic, logic, and comparison operations with

two images or with an image and a constant value.

Analytic Geometry

Frequency Domain Analysis

Barcode I/O Functions that find and read barcodes.

LCD Functions that find and read seven-segment LCD characters.

Meter Functions that return the arc information of a meter and read the meter.

Utilities Functions that return structures, and a function that returns a pointer to

OCR Functions that perform optical character recognition on an image.

Classification Functions that classify an image or feature vector.

Obsolete Functions that are no longer necessary but may exist in older applications.

Functions that perform basic geometric calculations on an image.

Functions for the extraction and manipulation of complex planes. Functions of this type perform Fast Fourier Transform (FFT), inverse FFT, truncation, attenuation, addition, subtraction, multiplication, and division of complex images.

predefined convolution matrices.

IMAQ Machine Vision Function Tree

The IMAQ Machine Vision function tree (NIMachineVision.fp) contains separate classes corresponding to groups or types of functions. Table 1-2 lists the IMAQ Machine Vision function types and gives a description of each type.

Table 1-2. IMAQ Machine Vision Function Types

Function Type Description

Coordinate Transform Functions that find coordinate transforms based on image contents.

Count and Measure Objects Function that counts and measures objects in an image.

Find Patterns Function that finds patterns in an image.

Locate Edges Functions that locate different types of edges in an image.

Chapter 1 Introduction to IMAQ Vision

Table 1-2. IMAQ Machine Vision Function Types (Continued)

Function Type Description

Measure Distances Functions that measure distances between objects in an image.

Measure Intensities Functions that measure light intensities in various shaped regions

within an image.

Select Region of Interest Functions that allow a user to select a specific region of interest in

an image.

Creating IMAQ Vision Applications

Figures 1-1 and 1-2 illustrate the steps for creating an application with IMAQ Vision. Figure 1-1 describes the general steps to designing a Vision application. The last step in Figure 1-1 is expanded upon in Figure 1-2. You can use a combination of the items in the last step to create your IMAQ Vision application. Refer to the corresponding chapter listed to the side of the item for more information about items in either diagram.

IMAQ Vision for LabWindows/CVI User Manual 1-4 ni.com

Chapter 1 Introduction to IMAQ Vision

Set Up Your Imaging System

Chapter 2:

Measurement-Ready

Getting

Images

Calibrate Your Imaging System

Create an Image

Acquire or Read an Image

Display an Image

Attach Calibration Information

Analyze an Image

Improve an Image

Make Measurements or Identify Objects

in an Image Using

Grayscale or Color Measurements, and/or

Particle Analysis, and/or

Machine Vision

Chapter 6: Calibration

Figure 1-1. General Steps for Designing a Vision Application

Note

Diagram items enclosed with dashed lines are optional steps.

Chapter 1 Introduction to IMAQ Vision

Chapter 5:

Particle

Analysis

Chapter 4:

Grayscale and Color

Measurements

Create a Binary Image

Improve a Binary Image

Make Particle Measurements

Grayscale Statistics

Define Regions of Interest

Measure

Find Measurement Points

Convert Pixel Coordinates to

Real-World Coordinates

Make Measurements

Measure

Color Statistics

Locate Objects to Inspect

Set Search Areas

Identify Parts Under Inspection

Classify Objects

Display Results

Read

Characters

Read

Symbologies

Chapter 6: Machine Vision

Figure 1-2. Inspection Steps for Building a Vision Application

Note

Diagram items enclosed with dashed lines are optional steps.

IMAQ Vision for LabWindows/CVI User Manual 1-6 ni.com

Getting Measurement-Ready Images

This chapter describes how to set up your imaging system, acquire and display an image, analyze the image, and prepare the image for additional processing.

Set Up Your Imaging System

Before you acquire, analyze, and process images, you must set up your imaging system. How you set up your system depends on your imaging environment and the type of analysis and processing you need to do. Your imaging system should produce images with high enough quality so that you can extract the information you need from the images.

Complete the following steps to set up your imaging system.

1. Determine the type of equipment you need given your space constraints and the size of the object you need to inspect. Refer to Chapter 3, System Setup and Calibration, of the IMAQ Vision Concepts Manual for more information.

a. Make sure your camera sensor is large enough to satisfy your

minimum resolution requirement.

b. Make sure your lens has a depth of field high enough to keep all

of your objects in focus regardless of their distance from the lens. Also, make sure your lens has a focal length that meets your needs.

c. Make sure your lighting provides enough contrast between the

object under inspection and the background for you to extract the information you need from the image.

2. Position your camera so that it is perpendicular to the object under inspection. If your camera acquires images of the object from an angle, perspective errors occur. Even though you can compensate for these errors with software, NI recommends that you use a perpendicular inspection angle to obtain the most accurate results.

Chapter 2 Getting Measurement-Ready Images

3. Select an IMAQ device that meets your needs. National Instruments offers several IMAQ devices, including analog color and monochrome devices as well as digital devices. Visit information about IMAQ devices.

4. Configure the driver software for your image acquisition device. If you have a National Instruments image acquisition device, configure the NI-IMAQ driver software through MAX. Open MAX by double-clicking the Measurement & Automation Explorer icon on your desktop. Refer to the NI-IMAQ User Manual and the Measurement and Automation Explorer Help for IMAQ for more information.

Calibrate Your Imaging System

After you set up your imaging system, you may want to calibrate your system to assign real-world coordinates to pixel coordinates. This allows you to compensate for perspective and nonlinear errors inherent in your imaging system.

Perspective errors occur when your camera axis is not perpendicular to the object under inspection. Nonlinear distortion may occur from aberrations in the camera lens. Perspective errors and lens aberrations cause images to appear distorted. This distortion misplaces information in an image, but it does not necessarily destroy the information in the image.

ni.com/imaq for more

Use simple calibration if you only want to assign real-world coordinates to pixel coordinates. Use perspective and nonlinear distortion calibration if you need to compensate for perspective errors and nonlinear lens distortion. For detailed information about calibration, refer to Chapter 5, Performing

Machine Vision Tasks.

Create an Image

To create an image in IMAQ Vision for LabWindows/CVI, call

imaqCreateImage(). This function returns an image reference you can

use when calling other IMAQ Vision functions. The only limitation to the size and number of images you can acquire and process is the amount of memory on your computer. When you create an image, specify the type of the image. Table 2-1 lists the valid image types.

IMAQ Vision for LabWindows/CVI User Manual 2-2 ni.com

Chapter 2 Getting Measurement-Ready Images

Table 2-1. IMAQ Vision for LabWindows/CVI Image Types

Val ue Description

IMAQ_IMAGE_U8

IMAQ_IMAGE_I16

IMAQ_IMAGE_SGL

IMAQ_IMAGE_COMPLEX 2 × 32 bits per pixel—floating point, native format after a Fast

8 bits per pixel—unsigned, standard monochrome

16 bits per pixel—signed, monochrome

32 bits per pixel—floating point, monochrome

Fourier Transform (FFT)

IMAQ_IMAGE_RGB

IMAQ_IMAGE_HSL

IMAQ_IMAGE_RGB_U64

32 bits per pixel—standard color

32 bits per pixel—color

64 bits per pixel—standard color

You can create multiple images by executing imaqCreateImage() as many times as you want. Determine the number of required images through an analysis of your intended application. The decision is based on different processing phases and your need to keep the original image after each processing step. The decision to keep an image occurs before each processing step.

When you create an image, IMAQ Vision creates an internal image structure to hold properties of the image, such as its name and border size. However, no memory is allocated to store the image pixels at this time. IMAQ Vision functions automatically allocate the appropriate amount of memory when the image size is modified. For example, functions that acquire or resample an image alter the image size, so they allocate the appropriate memory space for the image pixels. The return value of

imaqCreateImage() is a pointer to the image structure. Supply this

pointer as an input to all subsequent IMAQ Vision functions.

Most functions in the IMAQ Vision library require one or more image pointers. The number of image pointers a function takes depends on the image processing function and the type of image you want to use. Some IMAQ Vision functions act directly on the image and require only one image pointer. Other functions that process the contents of images require pointers to the source image(s) and to a destination image.

At the end of your application, dispose of each image that you created using

imaqDispose().

Chapter 2 Getting Measurement-Ready Images

Source and Destination Images

Some IMAQ Vision functions that modify the contents of an image have source image and destination image input parameters. The source image receives the image to process. The destination image receives the processing results. The destination image can receive either another image or the original, depending on your goals. If you do not want the contents of the original image to change, use separate source and destination images. If you want to replace the original image with the processed image, pass the same image as both the source and destination.

Depending on the function, the image type of the destination image can be the same or different than the image type of the source image. The function descriptions in the IMAQ Vision for LabWindows/CVI Function Reference include the type of images you can use as image inputs and outputs. IMAQ Vision resizes the destination image to hold the result if the destination is not the appropriate size.

The following examples illustrate source and destination images with

imaqTranspose():

•

imaqTranspose(myImage, myImage);

This function creates a transposed image using the same image for the source and destination. The contents of

•

imaqTranspose(myTransposedImage, myImage);

This function creates a transposed image and stores it in a destination different from the source. The and

myTransposedImage contains the result.

myImage change.

myImage image remains unchanged,

Functions that perform arithmetic or logical operations between two images have two source images and a destination image. You can perform an operation between two images and then either store the result in a separate destination image or in one of the two source images. In the latter case, make sure you no longer need the original data in the source image before storing the result over the data.

The following examples show the possible combinations using

imaqAdd():

•

imaqAdd(myResultImage, myImageA, myImageB);

This function adds two source images (myImageA and myImageB) and stores the result in a third image (

myResultImage). Both source

images remain intact after processing.

IMAQ Vision for LabWindows/CVI User Manual 2-4 ni.com

• imaqAdd(myImageA, myImageA, myImageB);

This function adds two source images and stores the result in the first source image.

•

imaqAdd(myImageB, myImageA, myImageB);

This function adds two source images and stores the result in the second source image.

Most operations between two images require that the images have the same type and size. However, some arithmetic operations can work between two different types of images, such as 8-bit and 16-bit images.

Some functions perform operations that populate an image. Examples of this type of operation include reading a file, acquiring an image from an IMAQ device, or transforming a 2D array into an image. This type of function can modify the size of an image.

Some functions take an additional mask parameter. The presence of this parameter indicates that the processing or analysis is dependent on the contents of another image, the image mask.

Note The image mask must be an 8-bit image.

Chapter 2 Getting Measurement-Ready Images

If you want to apply a processing or analysis function to the entire image, pass NULL for the image mask. Passing the same image to both the source image and image mask also gives the same effect as passing NULL for the image mask, except in this case the source image must be an 8-bit image.

Acquire or Read an Image

After you create an image reference, you can acquire an image into your imaging system in three ways. You can acquire an image with a camera through your IMAQ device, load an image from a file stored on your computer, or convert data stored in a 2D array to an image. Functions that acquire images, load images from file, or convert data from a 2D array to an image automatically allocate the memory space required to accommodate the image data.

Chapter 2 Getting Measurement-Ready Images

Acquiring an Image

Use one of the following methods to acquire images with a National Instruments IMAQ device.

• Acquire a single image using this function, it initializes the IMAQ device and acquires the next incoming video frame. Use this function for low-speed single capture applications where ease of programming is essential.

• Acquire a single image using function, it acquires the next incoming video frame on an IMAQ device you have already initialized using i

mgSessionOpen(). Use this function for high-speed single capture

applications.

• Acquire images continually through a grab acquisition. Grab functions perform high-speed acquisitions that loop continually on one buffer. Use

imaqSetupGrab() to start the acquisition. Use imaqGrab()

to return a copy of the current image. Use to stop the acquisition.

• Acquire a fixed number of images using a sequence acquisition. Set up the acquisition using

imaqStartAcquisition() to acquire the number of images you

requested during setup. If you want to acquire only certain images, supply of frames to skip after each acquired frame.

• Acquire images continually through a ringed buffer acquisition. Set up the acquisition using

imaqStartAcquisition() to start acquiring images into the

acquired ring buffer. To get an image from the ring, call

imaqExtractFromRing() or imaqCopyRing(). Use imaqStopAcquisition() to stop the acquisition.

imaqEasyAcquire(). When you call

imaqSnap(). When you call this

imgInterfaceOpen() and

imaqStopAcquisition()

imaqSetupSequence(). Use

imaqSetupSequence() with a table describing the number

imaqSetupRing(). Use

Note You must use imgClose() to release resources associated with the image

acquisition device.

Reading a File

Use imaqReadFile() to open and read data from a file stored on your computer into the image reference. You can read from image files stored in several standard formats: BMP, TIFF, JPEG, PNG, and AIPD. The software automatically converts the pixels it reads into the type of image you pass in.

IMAQ Vision for LabWindows/CVI User Manual 2-6 ni.com

Chapter 2 Getting Measurement-Ready Images

Use imaqReadVisionFile() to open an image file containing additional information, such as calibration information, template information for pattern matching, or overlay information. For more information about pattern matching templates and overlays, refer to Chapter 5, Performing

Machine Vision Tasks.

You can also use properties—such as image size, recommended image type, and calibration units—without actually reading all the image data.

Converting an Array to an Image

Use imaqArrayToImage() to convert a 2D array to an image. You can also use

imaqImageToArray() to convert an image to a 2D array.

Display an Image

Display an image in an external window using imaqDisplayImage(). You can display images in 16 different external windows. Use the other display functions to configure the appearance of each external window. Properties you can set include whether the window has scroll bars, a title bar, and whether it is resizable. You can also use position the external image window at a particular location on you monitor. Refer to the IMAQ Vision for LabWindows/CVI Function Reference for a complete list of Display functions.

Note Image windows are not LabWindows/CVI panels. They are managed directly by

IMAQ Vision .

You can use a color palette to display grayscale images by applying a color palette to the window. Use color palettes. For example, if you need to display a binary image—an image containing particle regions with pixel values of 1 and a background region with pixel values of 0—apply the predefined binary palette. For more information about color palettes, refer to Chapter 2, Display, of the IMAQ Vision Concepts Manual.

imaqGetFileInfo() to retrieve image

imaqMoveWindow() to

imaqSetWindowPalette() to set predefined

Note At the end of your application, close all open external windows using

imaqCloseWindow().

Chapter 2 Getting Measurement-Ready Images

Attach Calibration Information

If you want to attach the calibration information of the current setup to each image you acquire, use function takes in a source image containing the calibration information and a destination image that you want to calibrate. The output image is your inspection image with the calibration information attached to it. For detailed information about calibration, refer to Chapter 6, Calibrating

Images.

Note Because calibration information is part of the image, it is propagated throughout

the processing and analysis of the image. Functions that modify the image size, such as geometrical transforms, void the calibration information. Use to save the image and all of the attached calibration information to a file.

Analyze an Image

After you acquire and display an image, you may want to analyze the contents of the image for the following reasons:

• To determine whether the image quality is high enough for your inspection task.

• To obtain the values of parameters that you want to use in processing functions during the inspection process.

imaqCopyCalibrationInfo(). This

imaqWriteVisionFile()

The histogram and line profile tools can help you analyze the quality of your images.

Use

imaqHistogram() to analyze the overall grayscale distribution in the

image. Use the histogram of the image to analyze two important criteria that define the quality of an image—saturation and contrast. If your image is underexposed, or does not have enough light, the majority of your pixels will have low intensity values, which appear as a concentration of peaks on the left side of your histogram. If your image is overexposed, or has too much light, the majority of your pixels will have high intensity values, which appear as a concentration of peaks on the right side of your histogram. If your image has an appropriate amount of contrast, your histogram will have distinct regions of pixel concentrations. Use the histogram information to decide if the image quality is high enough to separate objects of interest from the background.

IMAQ Vision for LabWindows/CVI User Manual 2-8 ni.com

Chapter 2 Getting Measurement-Ready Images

If the image quality meets your needs, use the histogram to determine the range of pixel values that correspond to objects in the image. You can use this range in processing functions, such as determining a threshold range during particle analysis.

If the image quality does not meet your needs, try to improve the imaging conditions to get the necessary image quality. You may need to re-evaluate and modify each component of your imaging setup, including lighting equipment and setup, lens tuning, camera operation mode, and acquisition device parameters. If you reach the best possible conditions with your setup but the image quality still does not meet your needs, try to improve the image quality using the image processing techniques described in the Improve an Image section of this chapter.

Use

imaqLineProfile() to get the pixel distribution along a line in the

image, or use one-dimensional path in the image. By looking at the pixel distribution, you can determine if the image quality is high enough to provide you with sharp edges at object boundaries. Also, you can determine if the image is noisy and identify the characteristics of the noise.

If the image quality meets your needs, use the pixel distribution information to determine some parameters of the inspection functions you want to use. For example, use the information from the line profile to determine the strength of the edge at the boundary of an object. You can input this information into along the line.

imaqROIProfile() to get the pixel distribution along a

imaqEdgeTool2() to find the edges of objects

Improve an Image

Using the information you gathered from analyzing your image, you may want to improve the quality of your image for inspection. You can improve your image with lookup tables, filters, grayscale morphology, and FFTs.

Chapter 2 Getting Measurement-Ready Images

Lookup Tables

Apply lookup table (LUT) transformations to highlight image details in areas containing significant information at the expense of other areas. A LUT transformation converts input grayscale values in the source image into other grayscale values in the transformed image. IMAQ Vision provides four functions that directly or indirectly apply lookup tables to images.

•

imaqMathTransform()—Converts the pixel values of an image

by eplacing them with values from a predefined lookup table. IMAQ Vision has seven predefined lookup tables based on mathematical transformations. For more information about these lookup tables, refer to Chapter 5, Image Processing, of the IMAQ Vision Concepts Manual.

•

imaqLookup()—Converts the pixel values of an image by replacing

them with values from a user-defined lookup table.

•

imaqEqualize()—Distributes the grayscale values evenly within a

given grayscale range. Use in images containing few grayscale values.

•

imaqInverse()—Inverts the pixel intensities of an image to

compute the negative of the image. For example, use before applying an automatic threshold to your image if the background pixels are brighter than the object pixels.

imaqEqualize() to increase the contrast

imaqInverse()

Filters

Filter your image when you need to improve the sharpness of transitions in the image or increase the overall signal-to-noise ratio of the image. You can choose either a lowpass or highpass filter depending on your needs.

Lowpass filters remove insignificant details by smoothing the image,

removing sharp details, and smoothing the edges between the objects and the background. You can use lowpass filter with

imaqConvolve() or imaqNthOrderFilter().

Highpass filters emphasize details, such as edges, object boundaries,

or cracks. These details represent sharp transitions in intensity value. You can define your own highpass filter with

imaqNthOrderFilter(), or you can use a predefined highpass filter

with

imaqEdgeFilter() or imaqCannyEdgeFilter(). The

imaqEdgeFilter() function allows you to find edges in an image using

predefined edge detection kernels, such as the Sobel, Prewitt, and Roberts kernels.

IMAQ Vision for LabWindows/CVI User Manual 2-10 ni.com

imaqLowPass() or define your own

imaqConvolve() or

Convolution Filter

The imaqConvolve() function allows you to use a predefined set of lowpass and highpass filters. Each filter is defined by a kernel of coefficients. Use predefined kernels do not meet your needs, define your own custom filter using a 2D array of floating point numbers.

Nth Order Filter

The imaqNthOrderFilter() function allows you to define a lowpass or highpass filter depending on the value of N that you choose. One specific Nth order filter, the median filter, removes speckle noise, which appears as small black and white dots. Use filter. For more information about Nth order filters, refer to Chapter 5, Image Processing, of the IMAQ Vision Concepts Manual.

Grayscale Morphology

Perform grayscale morphology when you want to filter grayscale features of an image. Grayscale morphology helps you remove or enhance isolated features, such as bright pixels on a dark background. Use these transformations on a grayscale image to enhance non-distinct features before thresholding the image in preparation for particle analysis.

Chapter 2 Getting Measurement-Ready Images

imaqGetKernel() to retrieve predefined kernels. If the

imaqMedianFilter() to apply a median

Grayscale morphological transformations compare a pixel to those pixels surrounding it. The transformation keeps the smallest pixel values when performing an erosion or keeps the largest pixel values when performing a dilation.

Refer to Chapter 5, Image Processing, of the IMAQ Vision Concepts Manual for more information about grayscale morphology transformations.

Use

imaqGrayMorphology() to perform one of the following seven

transformations:

• Erosion—Reduces the brightness of pixels that are surrounded by neighbors with a lower intensity.

• Dilation—Increases the brightness of pixels surrounded by neighbors with a higher intensity. A dilation produces the opposite effect of an erosion.

• Opening—Removes bright pixels isolated in dark regions and smooths boundaries.

Chapter 2 Getting Measurement-Ready Images

• Closing—Removes dark pixels isolated in bright regions and smooths boundaries.

• Proper-opening—Removes bright pixels isolated in dark regions and smooths the inner contours of particles.

• Proper-closing—Removes dark pixels isolated in bright regions and smooths the inner contours of particles.

• Auto-median—Generates simpler particles that have fewer details.

FFT

Use the Fast Fourier Transform (FFT) to convert an image into its frequency domain. In an image, details and sharp edges are associated with mid to high spatial frequencies because they introduce significant gray-level variations over short distances. Gradually varying patterns are associated with low spatial frequencies.

An image can have extraneous noise, such as periodic stripes, introduced during the digitization process. In the frequency domain, the periodic pattern is reduced to a limited set of high spatial frequencies. Also, the imaging setup may produce non-uniform lighting of the field of view, which produces an image with a light drift superimposed on the information you want to analyze. In the frequency domain, the light drift appears as a limited set of low frequencies around the average intensity of the image, the DC component.

You can use algorithms working in the frequency domain to isolate and remove these unwanted frequencies from your image. Complete the following steps to obtain an image in which the unwanted pattern has disappeared but the overall features remain.

1. Use

imaqFFT() to convert an image from the spatial domain to the

frequency domain. This function computes the FFT of the image and results in a complex image representing the frequency information of your image.

2. Improve your image in the frequency domain with a lowpass or highpass frequency filter. Specify which type of filter to use with

imaqAttenuate() or imaqTruncate(). Lowpass filters smooth

noise, details, textures, and sharp edges in an image. Highpass filters emphasize details, textures, and sharp edges in images, but they also emphasize noise.

• Lowpass attenuation—The amount of attenuation is directly

proportional to the frequency information. At low frequencies, there is little attenuation. As the frequencies increase, the

IMAQ Vision for LabWindows/CVI User Manual 2-12 ni.com

Chapter 2 Getting Measurement-Ready Images

attenuation increases. This operation preserves all of the zero frequency information. Zero frequency information corresponds to the DC component of the image or the average intensity of the image in the spatial domain.

• Highpass attenuation—The amount of attenuation is inversely proportional to the frequency information. At high frequencies, there is little attenuation. As the frequencies decrease, the attenuation increases. The zero frequency component is removed entirely.

• Lowpass truncation—Frequency components above the ideal cutoff frequency are removed, and the frequencies below it remain unaltered.

• Highpass truncation—Frequency components above the ideal cutoff frequency remain unaltered, and the frequencies below it are removed.

3. To transform your image back to the spatial domain, use

imaqInverseFFT().

Complex Image Operations

The imaqExtractComplexPlane() and

imaqReplaceComplexPlane() functions allow you to access, process,

and update independently the real and imaginary planes of a complex image. You can also convert planes of a complex image to an array and back with

imaqArrayToComplexPlane().

imaqComplexPlaneToArray() and

Making Grayscale and Color Measurements

This chapter describes how to take measurements from grayscale and color images. You can make inspection decisions based on image statistics, such as the mean intensity level in a region. Based on the image statistics, you can perform many machine vision inspection tasks on grayscale or color images, such as detecting the presence or absence of components, detecting flaws in parts, and comparing a color component with a reference. Figure 3-1 illustrates the basic steps involved in making grayscale and color measurements.

Define Regions of Interest

Figure 3-1. Steps to Taking Grayscale and Color Measurements

Define Regions of Interest

A region of interest (ROI) is an area of an image in which you want to focus your image analysis. You can define an ROI interactively, programmatically, or with an image mask.

Defining Regions Interactively

You can interactively define an ROI in a window that displays an image. Use the tools from the IMAQ Vision tools palette to interactively define and manipulate an ROI.

Measure

Grayscale Statistics

Measure

Color Statistics

Chapter 3 Making Grayscale and Color Measurements

Table 3-1 describes each of the tools and the manner in which you use them.

Table 3-1. Tools Palette Functions

Icon Tool Name Function

Selection Tool Select an ROI in the image and adjust the position of its control

points and contours.

Action: Click the desired ROI or control points.

Point Select a pixel in the image.

Action: Click the desired position.

Line Draw a line in the image.

Action: Click the initial position, move the cursor to the final position, and click again.

Rectangle Draw a rectangle or square in the image.

Action: Click one corner and drag to the opposite corner.

Rotated Rectangle Draw a rotated rectangle in the image.

Action: Click one corner and drag to the opposite corner to create the rectangle. Then, click the lines inside the rectangle and drag to adjust the rotation angle.

Oval Draw an oval or circle in the image.

Action: Click the center position and drag to the desired size.

Annulus Draw an annulus in the image.

Action: Click the center position and drag to the desired size. Adjust the inner and outer radii, and adjust the start and end angles.

Broken Line Draw a broken line in the image.

Action: Click to place a new vertex and double-click to complete the ROI element.

Polygon Draw a polygon in the image.

Action: Click to place a new vertex and double-click to complete the ROI element.

IMAQ Vision for LabWindows/CVI User Manual 3-2 ni.com

Chapter 3 Making Grayscale and Color Measurements

Table 3-1. Tools Palette Functions (Continued)

Icon Tool Name Function

Freehand Line Draw a freehand line in the image.

Action: Click the initial position, drag to the desired shape, and release the mouse button to complete the shape.

Freehand Region Draw a freehand region in the image.

Action: Click the initial position, drag to the desired shape, and release the mouse button to complete the shape.

Zoom Zoom-in or zoom-out in an image.

Action: Click the image to zoom in. Hold down the <Shift> key and click to zoom out.

Pan Pan around an image.

Action: Click an initial position, drag to the desired position, and release the mouse button to complete the pan.

Hold down the <Shift> key while drawing an ROI to constrain the ROI to the horizontal, vertical, or diagonal axes. Use the Selection Tool to position an ROI by its control points or vertices. ROIs are context sensitive, meaning that the cursor actions differ depending on the ROI with which you interact. For example, if you move your cursor over the side of a rectangle, the cursor changes to indicate that you can click and drag the side to resize the rectangle. If you want to draw more than one ROI in a window, hold down the <Ctrl> key while drawing additional ROIs.

Chapter 3 Making Grayscale and Color Measurements

You can display the IMAQ Vision tools palette as part of an ROI constructor window or in a separate, floating window. Follow these steps to invoke an ROI constructor and define an ROI from within the ROI constructor window:

1. Use

imaqConstructROI2() to display an image and the tools palette

in an ROI constructor window, as shown in Figure 3-2.

Figure 3-2. ROI Constructor

2. Select an ROI tool from the tools palette.

3. Draw an ROI on your image. Resize and reposition the ROI until it designates the area you want to inspect.

4. Click OK to output a descriptor of the region you selected. You can input this ROI descriptor into many analysis and processing functions. You can also convert the ROI descriptor into an image mask, which you can use to process selected regions in the image. Use

imaqROIToMask() to convert the ROI descriptor into an image mask.

You can also use

imaqSelectRect(), and imaqSelectAnnulus() to define regions

imaqSelectPoint(), imaqSelectLine(),

of interest. Complete the following steps to use these functions.

1. Call the function to display an image in an ROI Constructor window. Only the tools specific to that function are available for you to use.

2. Draw an ROI on your image. Resize or reposition the ROI until it covers the area you want to process.

IMAQ Vision for LabWindows/CVI User Manual 3-4 ni.com

Chapter 3 Making Grayscale and Color Measurements

3. Click OK to populate a structure representing the ROI. You can use

this structure as an input to a variety of functions, such as the following functions that measure grayscale intensity.

•

imaqLightMeterPoint()—Uses the output of

imaqSelectPoint()

• imaqLightMeterLine()—Uses the output of

imaqSelectLine()

• imaqLightMeterRect()—Uses the output of

imaqSelectRect()

Tools Palette Transformation

The tools palette, shown in Figure 3-3, automatically transforms from the palette on the left to the palette on the right when you manipulate an ROI tool in an image window. The palette on the right displays the characteristics of the ROI you are drawing.

Pixel Intensity

Image-type indicator (8-bit, 16-bit, Float, RGB, HSL, Complex)

Coordinates of the mouse on the active image window

Anchoring coordinates of a Region of Interest

Size of an active Region of Interest

Length and horizontal angle of a line region

Figure 3-3. Tools Palette Tools and Information

Chapter 3 Making Grayscale and Color Measurements

The following list describes how you can display the tools palette in a separate window and manipulate the palette.

•Use

imaqShowToolWindow() to display the tools palette in a floating

window.

•Use

imaqSetupToolWindow() to configure the appearance of the

tools palette.

•Use

imaqMoveToolWindow() to move the tools palette.

imaqCloseToolWindow() to close the tools palette.

If you want to draw an ROI without using an ROI constructor or displaying the tools palette in a separate window, use This function allows you to select a contour from the tools palette without opening the palette.

Defining Regions Programmatically

When you have an automated application, you may need to define regions of interest programmatically. To programmatically define an ROI, create the ROI using A contour is a shape that defines an ROI. You can create contours from points, lines, rectangles, ovals, polygons, and annuli. For example, to add a rectangular contour to an ROI, use

imaqCreateROI(), and then add the individual contours.

imaqSetCurrentTool().

imaqAddRectContour().

Specify regions by providing basic parameters that describe the region you want to define. For example, define a point by providing the x-coordinate and y-coordinate. Define a line by specifying the start and end coordinates. Define a rectangle by specifying the coordinates of the top, left point; the width and height; and in the case of a rotated rectangle, the rotation angle.

Defining Regions with Masks

You can define regions to process with image masks. An image mask is an 8-bit image of the same size as or smaller than the image you want to process. Pixels in the mask image determine whether the corresponding pixel in the source image needs to be processed. If a pixel in the image mask has a value different than 0, the corresponding pixel in the source image is processed. If a pixel in the image mask has a value of 0, the corresponding pixel in the source image is left unchanged.

When you need to make intensity measurements on particles in an image, you can use a mask to define the particles. First, threshold your image to make a new binary image. For more information about binary images, refer to Chapter 4, Performing Particle Analysis. You can input the binary image

IMAQ Vision for LabWindows/CVI User Manual 3-6 ni.com

or a labeled version of the binary image as a mask image to the intensity measurement function. If you want to make color comparisons, convert the binary image into an ROI descriptor using

Measure Grayscale Statistics

You can measure grayscale statistics in images using light meters or quantitative analysis functions. You can obtain the center of energy for an image with the centroid function.

Use

imaqLightMeterPoint() to measure the light intensity at a

point in the image. Use statistics along a line in the image, such as mean intensity, standard deviation, minimum intensity, and maximum intensity. Use

imaqLightMeterRect() to get the pixel value statistics within

a rectangular region in an image.

Use

imaqQuantify() to obtain the following statistics about the entire

image or individual regions in the image: mean intensity, standard deviation, minimum intensity, maximum intensity, area, and the percentage of the image that you analyzed. You can specify regions in the image with a labeled image mask. A labeled image mask is a binary image that has been processed so that each region in the image mask has a unique intensity value. Use

imaqLabel2() to label your image mask.

imaqLightMeterLine() to get pixel value

Chapter 3 Making Grayscale and Color Measurements

imaqMaskToROI().

Use

imaqCentroid() to compute the energy center of the image, or of a

region within an image.

Measure Color Statistics

Most image processing and analysis functions apply to 8-bit images. However, you can analyze and process individual components of a color image.

Using

imaqExtractColorPlanes(), you can break down a color image

into various sets of primary components, such as RGB (Red, Green, and Blue), HSI (Hue, Saturation, and Intensity), HSL (Hue, Saturation, and Luminance), or HSV (Hue, Saturation, and Value). Each component becomes an 8-bit or 16-bit image that you can process like any other grayscale image. Using reassemble a color image from a set of three 8-bit or 16-bit images, where each image becomes one of the three primary components. Figures 3-4 and 3-5 illustrate how a color image breaks down into its three primary components.

imaqReplaceColorPlanes(), you can

Chapter 3 Making Grayscale and Color Measurements

Color

Image

Red

Green

Blue

Hue

Saturation

Intensity

Hue

Saturation

Luminance

Hue

Saturation

Value

8-bit Image Processing

Red

Green

Blue

Hue

Saturation

Intensity

Hue

Saturation

Luminance

Hue

Saturation

Value

Color

Image

Figure 3-4. Primary Components of a 32-Bit Color Image

Color

Image

1664

Red

Green

Blue

161616

16-bit

Image

Processing

16161616

Red

Green

Blue

1664

Color

Image

Figure 3-5. Primary Components of a 64-Bit Color Image

Use imaqExtractColorPlanes() to extract the red, green, blue, hue saturation, intensity, luminance, or value plane of a color image into an 8-bit image.

Note You can also use imaqExtractColorPlanes() to process the red, green, and blue

components of a 64-bit image.

IMAQ Vision for LabWindows/CVI User Manual 3-8 ni.com

Comparing Colors

Chapter 3 Making Grayscale and Color Measurements

You can use the color matching capability of IMAQ Vision to compare or evaluate the color content of an image or regions in an image.

Complete the following steps to compare colors using color matching:

1. Select an image containing the color information that you want to use as a reference. The color information can consist of a single color or multiple dissimilar colors, such as red and blue.

2. Use the entire image or regions in the image to learn the color information using spectrum that contains a compact description of the color information in an image or ROI. Use the color spectrum to represent the learned color information for all subsequent matching operations. Refer to Chapter 14, Color Inspection, of the IMAQ Vision Concepts Manual for more information about color learning.

3. Define an entire image, a region, or multiple regions in an image as the inspection or comparison area.

4. Use

5. Use the color matching score as a measure of similarity between the

imaqMatchColor() to compare the learned color information to

the color information in the inspection regions. This function returns an array of scores that indicates how close the matches are to the learned color information.

reference color information and the color information in the image regions being compared.

imaqLearnColor(), which outputs a color

Learning Color Information

Choose the color information carefully when learning color information.

• Specify an image or regions in an image that contain the color or color information that you want to learn.

• Select the level of detail you want the for the learned color information.

• Choose colors that you want to ignore during matching.

Specifying the Color Information to Learn

Because color matching only uses color information to measure similarity, the image or regions in the image representing the object must contain only the significant colors that represent the object, as shown in Figure 3-6a. Figure 3-6b illustrates an unacceptable region containing background colors.

Chapter 3 Making Grayscale and Color Measurements

Figure 3-6. Template Color Information

a. b.

The following sections explain when to learn the color information associated with an entire image, a region in an image, or multiple regions in an image.

Using the Entire Image

You can use an entire image to learn the color spectrum that represents the entire color distribution of the image. In a fabric identification application, for example, an entire image can specify the color information associated with a certain fabric type, as shown in Figure 3-7.

Figure 3-7. Using the Entire Image to Learn Color Distribution

Using a Region in the Image

You can select a region in the image to provide the color information for comparison. A region is helpful for pulling out the useful color information in an image. Figure 3-8 shows an example of using a region that contains the color information that is important for the application.

IMAQ Vision for LabWindows/CVI User Manual 3-10 ni.com

Chapter 3 Making Grayscale and Color Measurements

Figure 3-8. Using a Single Region to Learn Color Distribution

Using Multiple Regions in the Image

The interaction of light with the object surface creates the observed color of that object. The color of a surface depends on the directions of illumination and the direction from which the surface is observed. Two identical objects may have different appearances because of a difference in positioning or a change in the lighting conditions.

Figure 3-9 shows how light reflects differently off of the 3D surfaces of the fuses, resulting in slightly different colors for identical fuses. Compare the 3-amp fuse in the upper row with the 3-amp fuse in the lower row. The difference in light reflection results in different color spectrums for identical fuses.

If you learn the color spectrum by drawing a region of interest around the 3-amp fuse in the upper row, and then do a color matching for the 3-amp fuse in the upper row, you get a very high match score—close to 1000. But the match score for the 3-amp fuse in the lower row is quite low—around

500. This problem could cause a mismatch for the color matching in a fuse

box inspection process.

The color learning algorithm of IMAQ Vision uses a clustering process to find the representative colors from the color information specified by one or multiple regions in the image. To create a representative color spectrum for all 3-amp fuses in the learning phase, draw an ROI around the 3-amp fuse in the upper row, hold down the <Shift> key, and draw another ROI around the 3-amp fuse in the lower row. The new color spectrum represents 3-amp fuses better and results in high match scores (around 800) for both 3-amp fuses. Use as many samples as you want in an image to learn the representative color spectrum for a specified template.

Chapter 3 Making Grayscale and Color Measurements

1 Regions Used to Learn Color Information

Figure 3-9. Using Multiple Regions to Learn Color Distribution

Choosing a Color Representation Sensitivity

When you learn a color, you need to specify the sensitivity required to specify the color information. An image containing a few, well-separated colors in the color space requires a lower sensitivity to describe the color than an image that contains colors that are close to one another in the color space. Use the sensitivity parameter of granularity you want to use to represent the colors. Refer to the Color

Sensitivity section of Chapter 5, Performing Machine Vision Tasks, for

more information about color sensitivity.

IMAQ Vision for LabWindows/CVI User Manual 3-12 ni.com

imaqLearnColor() to specify the

Chapter 3 Making Grayscale and Color Measurements

Ignoring Learned Colors

Ignore certain color components in color matching by replacing the corresponding component in the input color spectrum array to –1. For example, by replacing the last component in the color spectrum with –1, the white color is ignored during the color matching process. By replacing the second to last component in the color spectrum, the black color is ignored during the color matching process.

To ignore other color components in color matching, determine the index to the color spectrum by locating the corresponding bins in the color wheel, where each bin corresponds to a component in the color spectrum array. Ignoring certain colors such as the background color results in a more accurate color matching score. Ignoring the background color also provides more flexibility when defining the regions of interest in the color matching process. Ignoring other, non-background colors, such as the white color created by glare on a metallic surface, also improves the accuracy of the color matching. Experiment learning the color information about different parts of the images to determine which colors to ignore. Refer to Chapter 14, Color Inspection, of the IMAQ Vision Concepts Manual for more information about the color wheel and color bins.

Performing Particle Analysis

This chapter describes how to perform particle analysis on your images. Use particle analysis to find statistical information about particles—such as the area, location, and presence of particles. With this information, you can perform many machine vision inspection tasks, such as detecting flaws on silicon wafers or detecting soldering defects on electronic boards. Examples of how particle analysis can help you perform inspection tasks include locating structural defects on wood planks or detecting cracks on plastic sheets.

Figure 4-1 illustrates the steps involved in performing particle analysis.

Create a Binary Image

Improve a Binary Image

Make Particle Measurements

in Pixels or Real-World Units

Figure 4-1. Steps to Performing Particle Analysis

Create a Binary Image

Threshold your grayscale or color image to create a binary image. Creating a binary image separates the objects that you want to inspect from the background. The threshold operation sets the background pixels to 0 in the binary image while setting the object pixels to a non-zero value. Object pixels have a value of 1 by default, but you can set the object pixels to any value you choose.

You can use different techniques to threshold your image. If all the objects of interest in your grayscale image fall within a continuous range of intensities and you can specify this threshold range manually, use

imaqThreshold() to threshold your image.

Chapter 4 Performing Particle Analysis

If all the objects in your grayscale image are either brighter or darker than your background, you can use determine the optimal threshold range and threshold your image. Automatic thresholding techniques offer more flexibility than simple thresholds based on fixed ranges. Because automatic thresholding techniques determine the threshold level according to the image histogram, the operation is more independent of changes in the overall brightness and contrast of the image than a fixed threshold. These techniques are more resistant to changes in lighting, which makes them well suited for automated inspection tasks.

If your grayscale image contains objects that have multiple discontinuous grayscale values, use threshold ranges.

imaqAutoThreshold() to automatically

imaqMultithreshold() to specify multiple

If you need to threshold a color image, use You must specify threshold ranges for each of the color planes using either the RGB or HSL color model. The binary image resulting from a color threshold is an 8-bit binary image.

Improve the Binary Image

After you threshold your image, you may want to improve the resulting binary image with binary morphology. You can use primary binary morphology or advanced binary morphology to remove unwanted particles, separate connected particles, or improve the shape of particles. Primary morphology functions work on the image as a whole by processing pixels individually. Advanced morphology operations are built upon the primary morphological operators and work on particles as opposed to pixels. Refer to Chapter 9, Binary Morphology, of the IMAQ Vision Concepts Manual for lists of which morphology functions are primary and which are advanced.

The advanced morphology functions require that you specify the type of

connectivity to use. Use connectivity-4 when you want IMAQ Vision to

consider pixels to be part of the same particle only when the pixels touch along an adjacent edge. Use connectivity-8 when you want IMAQ Vision to consider pixels to be part of the same particle even if the pixels touch only at a corner. Refer to Chapter 9, Binary Morphology, of the IMAQ Vision Concepts Manual for more information about connectivity.

imaqColorThreshold().

Note Use the same type of connectivity throughout your application.

IMAQ Vision for LabWindows/CVI User Manual 4-2 ni.com

Removing Unwanted Particles

Use imaqRejectBorder() to remove particles that touch the border of the image. Reject particles on the border of the image when you suspect that the information about those particles is incomplete.

Use

imaqSizeFilter() to remove large or small particles that do

not interest you. You can also use the

IMAQ_POPEN methods in imaqMorphology() to remove small particles.

Unlike

imaqSizeFilter(), these three operations alter the size and

shape of the remaining particles.

Chapter 4 Performing Particle Analysis

IMAQ_ERODE, IMAQ_OPEN, and

Use the

IMAQ_HITMISS method of imaqMorphology() to locate

particular configurations of pixels, which you define with a structuring element. Depending on the configuration of the structuring element, the

IMAQ_HITMISS method can locate single isolated pixels, cross-shape or

longitudinal patterns, right angles along the edges of particles, and other user-specified shapes. Refer to Chapter 9, Binary Morphology, of the IMAQ Vision Concepts Manual for more information about structuring elements.

If you know enough about the shape features of the particles you want to keep, use

imaqParticleFilter2() to filter out particles that do not

interest you.

Separating Touching Particles

Use imaqSeparation() or apply an erosion or an open operation with

imaqMorphology() to separate touching objects. The

imaqSeparation() function is an advanced function that separates

particles without modifying their shapes. However, erosion and open operations alter the shape of all the particles.

Note A separation is a time-intensive operation compared to an erosion or open operation.

Consider using an erosion or open operation if speed is an issue with your application.

Improving Particle Shapes

Use imaqFillHoles() to fill holes in the particles. Use

imaqMorphology() to perform a variety of operations on the particles.

You can use the and

IMAQ_POPEN methods to smooth the boundaries of the particles. Open

and proper-open smooth the boundaries of the particle by removing small

IMAQ_AUTOM, IMAQ_CLOSE, IMAQ_PCLOSE, IMAQ_OPEN,

Chapter 4 Performing Particle Analysis

isthmuses while close widens the isthmuses. Close and proper-close fill small holes in the particle. Auto-median removes isthmuses and fills holes. Refer to Chapter 9, Binary Morphology, of the IMAQ Vision Concepts Manual for more information about these methods.

Make Particle Measurements

After you create a binary image and improve it, you can make particle measurements. IMAQ Vision can return the measurements in uncalibrated pixels or calibrated real-world units. With these measurements you can determine the location of particles and their shape features. Use the following functions to perform particle measurements:

•

imaqCountParticles()—This function returns the number of

particles in an image and calculates various measurements for each particle.

•

imaqMeasureParticle()—This function uses the calculations

from

imaqCountParticles() to return specific measurements of

a particle.

Table 4-1 lists all of the measurements that returns.

Table 4-1. Particle Measurements

Measurement Description

IMAQ_MT_AREA

IMAQ_MT_AREA_BY_IMAGE_AREA

IMAQ_MT_AREA_BY_PARTICLE_AND_HOLES_AREA

IMAQ_MT_AVERAGE_HORIZ_SEGMENT_LENGTH

IMAQ_MT_AVERAGE_VERT_SEGMENT_LENGTH

IMAQ_MT_BOUNDING_RECT_BOTTOM

IMAQ_MT_BOUNDING_RECT_TOP

imaqMeasureParticle()

Area of the particle

Percentage of the particle area covering the image area

Percentage of the particle area in relation to the area of its particle and holes

Average length of a horizontal segment in the particle

Average length of a vertical segment in the particle

Y-coordinate of the lowest particle point

Y-coordinate of the highest particle point

IMAQ Vision for LabWindows/CVI User Manual 4-4 ni.com

Chapter 4 Performing Particle Analysis

Table 4-1. Particle Measurements (Continued)

Measurement Description

IMAQ_MT_BOUNDING_RECT_LEFT

IMAQ_MT_BOUNDING_RECT_RIGHT

IMAQ_MT_BOUNDING_RECT_HEIGHT

IMAQ_MT_BOUNDING_RECT_WIDTH

IMAQ_MT_BOUNDING_RECT_DIAGONAL

IMAQ_MT_CENTER_OF_MASS_X

IMAQ_MT_CENTER_OF_MASS_Y

X-coordinate of the leftmost particle point

X-coordinate of the rightmost particle point

Distance between the y-coordinate of highest particle point and the y-coordinate of the lowest particle point

Distance between the x-coordinate of the leftmost particle point and the x-coordinate of the rightmost particle point

Distance between opposite corners of the bounding rectangle

X-coordinate of the point representing the average position of the total particle mass assuming every point in the particle has a constant density

Y-coordinate of the point representing the average position of the total particle mass assuming every point in the particle has a constant density

IMAQ_MT_COMPACTNESS_FACTOR

Area divided by the product of bounding rectangle width and bounding rectangle height

IMAQ_MT_CONVEX_HULL_AREA

Area of the smallest convex polygon containing all points in the particle

IMAQ_MT_CONVEX_HULL_PERIMETER

Perimeter of the smallest convex polygon containing all points in the particle

Chapter 4 Performing Particle Analysis

Table 4-1. Particle Measurements (Continued)

Measurement Description

IMAQ_MT_EQUIVALENT_ELLIPSE_MAJOR_AXIS

IMAQ_MT_EQUIVALENT_ELLIPSE_MINOR_AXIS

IMAQ_MT_EQUIVALENT_ELLIPSE_MINOR_AXIS_FERET

IMAQ_MT_EQUIVALENT_RECT_DIAGONAL

IMAQ_MT_EQUIVALENT_RECT_LONG_SIDE

IMAQ_MT_EQUIVALENT_RECT_SHORT_SIDE

IMAQ_MT_EQUIVALENT_RECT_SHORT_SIDE_FERET

Length of the major axis of the ellipse with the same perimeter and area as the particle

Length of the minor axis of the ellipse with the same perimeter and area as the particle

Length of the minor axis of the ellipse with the same area as the particle, and major axis equal in length to the max feret diameter

Distance between opposite corners of the rectangle with the same perimeter and area as the particle

Longest side of the rectangle with the same perimeter and area as the particle

Shortest side of the rectangle with the same perimeter and area as the particle

Shortest side of the rectangle with the same area as the particle, and longest side equal in length to the max feret diameter

IMAQ_MT_ELONGATION_FACTOR

Max feret diameter divided by equivalent rectangle short side (feret)

IMAQ_MT_FIRST_PIXEL_X

X-coordinate of the highest, leftmost particle pixel

IMAQ_MT_FIRST_PIXEL_Y

Y-coordinate of the highest, leftmost particle pixel

IMAQ_MT_HU_MOMENT_1

IMAQ_MT_HU_MOMENT_2

IMAQ_MT_HU_MOMENT_3

IMAQ_MT_HU_MOMENT_4

IMAQ Vision for LabWindows/CVI User Manual 4-6 ni.com

First Hu moment

Second Hu moment

Third Hu moment

Fourth Hu moment

Chapter 4 Performing Particle Analysis

Table 4-1. Particle Measurements (Continued)

Measurement Description

IMAQ_MT_HU_MOMENT_5

IMAQ_MT_HU_MOMENT_6

IMAQ_MT_HU_MOMENT_7

IMAQ_MT_HEYWOOD_CIRCULARITY_FACTOR

IMAQ_MT_HOLES_PERIMETER

IMAQ_MT_HYDRAULIC_RADIUS

IMAQ_MT_HOLES_AREA

IMAQ_MT_IMAGE_AREA

IMAQ_MT_MAX_FERET_DIAMETER

IMAQ_MT_MAX_FERET_DIAMETER_END_X

Fifth Hu moment

Sixth Hu moment

Seventh Hu moment

Perimeter divided by the circumference of a circle with the same area

Sum of the perimeters of each hole in the particle

Particle area divided by the particle perimeter

Sum of the areas of each hole in the particle

Area of the image

Distance between the start and end of the line segment connecting the two perimeter points that are the furthest apart

X-coordinate of the end of the line segment connecting the two perimeter points that are the furthest apart

IMAQ_MT_MAX_FERET_DIAMETER_END_Y

Y-coordinate of the end of the line segment connecting the two perimeter points that are the furthest apart

IMAQ_MT_MAX_FERET_DIAMETER_ORIENTATION

Angle of the line segment connecting the two perimeter points that are the furthest apart

IMAQ_MT_MAX_FERET_DIAMETER_START_X

X-coordinate of the start of the line segment connecting the two perimeter points that are the furthest apart

Chapter 4 Performing Particle Analysis

Table 4-1. Particle Measurements (Continued)

Measurement Description

IMAQ_MT_MAX_FERET_DIAMETER_START_Y

IMAQ_MT_MAX_HORIZ_SEGMENT_LENGTH_LEFT

IMAQ_MT_MAX_HORIZ_SEGMENT_LENGTH_RIGHT

IMAQ_MT_MAX_HORIZ_SEGMENT_LENGTH_ROW

IMAQ_MT_MOMENT_OF_INERTIA_XX

IMAQ_MT_MOMENT_OF_INERTIA_XY

IMAQ_MT_MOMENT_OF_INERTIA_YY

IMAQ_MT_MOMENT_OF_INERTIA_XXX

Y-coordinate of the start of the line segment connecting the two perimeter points that are the furthest apart

X-coordinate of the leftmost pixel in the longest row of contiguous pixels in the particle

X-coordinate of the rightmost pixel in the longest row of contiguous pixels in the particle

Y-coordinate of all of the pixels in the longest row of contiguous pixels in the particle

Moment of inertia in the x direction twice

Moment of inertia in the x and y directions

Moment of inertia in the y direction twice

Moment of inertia in the x direction three times

IMAQ_MT_MOMENT_OF_INERTIA_XXY

Moment of inertia in the x direction twice and the y direction once

IMAQ_MT_MOMENT_OF_INERTIA_XYY

Moment of inertia in the x direction once and the y direction twice

IMAQ_MT_MOMENT_OF_INERTIA_YYY

Moment of inertia in the y direction three times

IMAQ_MT_NORM_MOMENT_OF_INERTIA_XX

Normalized moment of inertia in the x direction twice

IMAQ_MT_NORM_MOMENT_OF_INERTIA_XY

Normalized moment of inertia in the x and y directions

IMAQ_MT_NORM_MOMENT_OF_INERTIA_YY

Normalized moment of inertia in the y direction twice

IMAQ Vision for LabWindows/CVI User Manual 4-8 ni.com

Chapter 4 Performing Particle Analysis

Table 4-1. Particle Measurements (Continued)

Measurement Description

IMAQ_MT_NORM_MOMENT_OF_INERTIA_XXX

IMAQ_MT_NORM_MOMENT_OF_INERTIA_XXY

IMAQ_MT_NORM_MOMENT_OF_INERTIA_XYY

IMAQ_MT_NORM_MOMENT_OF_INERTIA_YYY

IMAQ_MT_NUMBER_OF_HOLES

IMAQ_MT_NUMBER_OF_HORIZ_SEGMENTS

IMAQ_MT_NUMBER_OF_VERT_SEGMENTS

IMAQ_MT_ORIENTATION

IMAQ_MT_PERIMETER

Normalized moment of inertia in the x direction three times

Normalized moment of inertia in the x direction twice and the y direction once

Normalized moment of inertia in the x direction once and the y direction twice

Normalized moment of inertia in the y direction three times

Number of holes in the particle

Number of horizontal segments in the particle

Number of vertical segments in the particle

Angle of the line that passes through the particle center of mass about which the particle has the lowest moment of inertia

Length of the outer boundary of the particle

IMAQ_MT_PARTICLE_AND_HOLES_AREA

Area of a particle that completely covers the image

IMAQ_MT_RATIO_OF_EQUIVALENT_ELLIPSE_AXES

Equivalent ellipse major axis divided by equivalent ellipse minor axis

IMAQ_MT_RATIO_OF_EQUIVALENT_RECT_SIDES

Equivalent rectangle long side divided by equivalent rectangle short side

IMAQ_MT_SUM_X

Sum of all x-coordinates in the particle

IMAQ_MT_SUM_Y

Sum of all y-coordinates in the particle

Chapter 4 Performing Particle Analysis

Table 4-1. Particle Measurements (Continued)

Measurement Description

IMAQ_MT_SUM_XX

IMAQ_MT_SUM_XY

IMAQ_MT_SUM_YY

IMAQ_MT_SUM_XXX

IMAQ_MT_SUM_XXY

IMAQ_MT_SUM_XYY

IMAQ_MT_SUM_YYY

IMAQ_MT_TYPE_FACTOR

IMAQ_MT_WADDEL_DISK_DIAMETER

Sum of all x-coordinates squared in the particle

Sum of all x-coordinates multiplied by y-coordinates in the particle

Sum of all y-coordinates squared in the particle

Sum of all x-coordinates cubed in the particle

Sum of all x-coordinates squared multiplied by y-coordinates in the particle

Sum of all x-coordinates multiplied by y-coordinates squared in the particle

Sum of all y-coordinates cubed in the particle

Factor relating area to moment of inertia

Diameter of a disk with the same area as the particle

IMAQ Vision for LabWindows/CVI User Manual 4-10 ni.com

Performing Machine Vision Tasks

This chapter describes how to perform many common machine vision inspection tasks. The most common inspection tasks are detecting the presence or absence of parts in an image and measuring the dimensions of parts to see if they meet specifications.

Measurements are based on characteristic features of the object represented in the image. Image processing algorithms traditionally classify the type of information contained in an image as edges, surfaces and textures, or patterns. Different types of machine vision algorithms leverage and extract one or more types of information.

Edge detectors and derivative techniques—such as rakes, concentric rakes, and spokes—use edges represented in the image. They locate, with high accuracy, the position of the edge of an object in the image. For example, a technique called clamping uses edge locations to measure the width of a part. You can combine multiple edge locations to compute intersection points, projections, circles, or ellipse fits.

Pattern matching algorithms use edges and patterns. Pattern matching can locate, with very high accuracy, the position of fiducials or characteristic features of the part under inspection. Those locations can then be combined to compute lengths, angles, and other object measurements.

The robustness of your measurement relies on the stability of your image acquisition conditions. Sensor resolution, lighting, optics, vibration control, part fixture, and general environment are key components of the imaging setup. All the elements of the image acquisition chain directly affect the accuracy of the measurements.

Chapter 5 Performing Machine Vision Tasks

Figure 5-1 illustrates the basic steps involved in performing machine vision inspection tasks.

Locate Objects to Inspect

Set Search Areas

Find Measurement Points

Convert Pixel Coordinates to

Real-World Coordinates

Figure 5-1. Steps to Performing Machine Vision

Note

Diagram items enclosed with dashed lines are optional steps.

Locate Objects to Inspect

In a typical machine vision application, you extract measurements from ROIs rather than the entire image. To use this technique, the parts of the object you are interested in must always appear inside the ROI you define.

If the object under inspection is always at the same location and orientation in the images you need to process, defining an ROI is simple. Refer to the Set Search Areas section of this chapter for information about selecting an ROI.

Make Measurements

Identify Parts Under Inspection

Classify Objects

Display Results

Read

Characters

Read

Symbologies

Often, the object under inspection appears rotated or shifted relative to the reference image in which you located the object. When this occurs, the ROIs need to shift and rotate with the parts of the object in which you are interested. To move the ROIs with the object, you must define a reference coordinate system relative to the object in the reference image. During the measurement process, the coordinate system moves with the object when

IMAQ Vision for LabWindows/CVI User Manual 5-2 ni.com

Chapter 5 Performing Machine Vision Tasks

it appears shifted and rotated in the image you need to process. This coordinate system is referred to as the measurement coordinate system. The measurement methods automatically move the ROIs to the correct position using the position of the measurement coordinate system with respect to the reference coordinate system. Refer to Chapter 13, Dimensional Measurements, of the IMAQ Vision Concepts Manual for information about coordinate systems.

You can build a coordinate transform using edge detection or pattern matching. The output of the edge detection and pattern matching functions that build a coordinate system are the origin, angle, and axes direction of the coordinate system. Some machine vision functions take this output and adjust the regions of inspection automatically. You can also use these outputs to programmatically move the regions of inspection relative to the object.

Chapter 5 Performing Machine Vision Tasks

Using Edge Detection to Build a Coordinate Transform

You can build a coordinate transform using two edge detection techniques. Use

imaqFindTransformRect() to define a coordinate system using

one rectangular region. Use coordinate system using two independent rectangular regions. Follow these steps to build a coordinate transform using edge detection.

Note To use this technique, the object cannot rotate more than ±65° in the image.

1. Specify one or two rectangular ROIs.

a. If you use

imaqFindTransformRect(), specify one rectangular

ROI that includes part of two straight, nonparallel boundaries of the object, as shown in Figure 5-2. This rectangular region must be large enough to include these boundaries in all the images you want to inspect.

imaqFindTransformRects() to define a

1 Search Area for the Coordinate System 2 Object Edges

a. b.

Figure 5-2. Coordinate Systems of a Reference Image and Inspection Image

3 Origin of the Coordinate System 4 Measurement Area

IMAQ Vision for LabWindows/CVI User Manual 5-4 ni.com

Chapter 5 Performing Machine Vision Tasks

b. If you use imaqFindTransformRects(), specify two

rectangular objects, each containing one separate, straight boundary of the object, as shown in Figure 5-3. The boundaries cannot be parallel. The regions must be large enough to include the boundaries in all the images you want to inspect.

1 Primary Search Area 2 Secondary Search Area

3 Origin of the Coordinate System 4 Measurement Area

b.a.

Figure 5-3. Locating Coordinate System Axes with Two Search Areas

2. Use the options parameter to choose the options you need to locate the edges on the object, the coordinate system axis direction, and the results that you want to overlay onto the image. Set the options parameter to

NULL to use the default options.

3. Choose the mode for the function. To build a coordinate transform for the first time, set the mode parameter to

IMAQ_FIND_REFERENCE.

To update the coordinate transform in subsequent images, set this mode to

IMAQ_UPDATE_TRANSFORM.

Chapter 5 Performing Machine Vision Tasks

Using Pattern Matching to Build a Coordinate Transform

You can build a coordinate transform using pattern matching. Use

imaqFindTransformPattern() to define a coordinate system based on

the location of a reference feature. Use this technique when the object under inspection does not have straight, distinct edges. Complete the following steps to build a coordinate reference system using pattern matching.

Note The object may rotate 360° in the image using this technique if you use

rotation-invariant pattern matching.

1. Define a template that represents the part of the object that you want to use as a reference feature. Refer to the Find Measurement Points section of this chapter for more information about defining a template.

2. Define a rectangular ROI in which you expect to find the template.

3. Use the options parameter to select your options for finding the pattern and the results that you want to overlay onto the image. When setting the

Mode element, select IMAQ_MATCH_ROTATION_INVARIANT when

you expect your template to appear rotated in the inspection images. Otherwise, select parameter to

4. Choose the mode for the function. To build a coordinate transform for the first time, set the mode parameter to To update the coordinate system in subsequent images, set the mode parameter to

IMAQ_MATCH_SHIFT_INVARIANT. Set the options

NULL to use the default options.

IMAQ_FIND_REFERENCE.

IMAQ_UPDATE_TRANSFORM.

IMAQ Vision for LabWindows/CVI User Manual 5-6 ni.com

Chapter 5 Performing Machine Vision Tasks

Choosing a Method to Build the Coordinate Transform

Figure 5-4 guides you through choosing the best method for building a coordinate transform for your application.

Start

Object positioning

accuracy better

than ±65 degrees.

Ye s

The object under inspection has a straight, distinct edge (main axis).

Ye s

The object contains a

second distinct edge not parallel

to the main axis in the same

search area.

Ye s

Build a

coordinate transformation

based on edge detection

using a single search area.

The object contains

a second distinct edge not

parallel to the main axis in a

separate search area.

Ye s

Build a coordinate transformation based on edge detection using two

distinct search areas.

Object positioning

accuracy better

than ±5 degrees.

Ye s

Build a coordinate

transformation based on

pattern matching

shift invariant strategy.

Build a coordinate

transformation based on

pattern matching

rotation invariant strategy.

End

Figure 5-4. Building a Coordinate Transform

Chapter 5 Performing Machine Vision Tasks

Set Search Areas

You use ROIs to define search areas in your images and limit the areas in which you perform your processing and inspection. You can define ROIs interactively or programmatically.

Defining Regions Interactively

Complete the following steps to interactively define an ROI:

1. Use

2. Select an ROI tool from the tools palette.

3. Draw an ROI on your image. Resize and reposition the ROI until it

4. Click OK to output a descriptor of the region you selected. You can

imaqConstructROI2() to display an image and the tools palette

in a window.

specifies the area you want to process.

input the ROI descriptor into many analysis and processing functions.

You can also use define ROIs. Complete the following steps to use these functions:

1. Call the function to display an image in a window. Only the tools specific to that function are available for you to use.

2. Select an ROI tool from the tools palette.

3. Draw an ROI on your image. Resize or reposition the ROI until it specifies the area you want to process.

Click OK to output a description of the ROI. You can use this description as an input for the following functions.

ROI Selection Function Measurement Function

imaqSelectRect() imaqFindPattern()

imaqSelectAnnulus() imaqFindCircularEdge()

imaqSelectRect() and imaqSelectAnnulus() to

imaqClampMax()

imaqClampMin()

imaqFindEdge()

imaqFindConcentricEdge()

IMAQ Vision for LabWindows/CVI User Manual 5-8 ni.com

Defining Regions Programmatically

When you have an automated application, you need to define ROIs programmatically. You can programmatically define regions in two ways:

• Specify the contours of the ROI.

• Specify individual structures by providing basic parameters that describe the region you want to define. You can specify a rotated rectangle by providing the coordinates of the center, the width, the height, and the rotation angle. You can specify an annulus by providing the coordinates of the center, inner radius, outer radius, start angle, and end angle. You can specify a point by setting its x-coordinates and y-coordinates. You can specify a line by setting the coordinates of the start and end points.

Refer to Chapter 3, Making Grayscale and Color Measurements, for more information about defining ROIs.

Find Measurement Points

After you set regions of inspection, locate points within those regions on which you can base measurements. You can locate measurement points using edge detection, pattern matching, color pattern matching, and color location.

Chapter 5 Performing Machine Vision Tasks

Finding Features Using Edge Detection

Use the edge detection tools to identify and locate sharp discontinuities in an image. Discontinuities typically represent abrupt changes in pixel intensity values, which characterize the boundaries of objects.

Chapter 5 Performing Machine Vision Tasks

Finding Lines or Circles

If you want to find points along the edge of an object and find a line describing the edge, use

imaqFindConcentricEdges(). The imaqFindEdge() function finds

edges based on rectangular search areas, as shown in Figure 5-5. The

imaqFindConcentricEdge() function finds edges based on annular

search areas.

imaqFindEdge() and

1 Search Region 2 Search Lines

3 Detected Edge Points 4 Line Fit to Edge Points

Figure 5-5. Finding a Straight Feature

IMAQ Vision for LabWindows/CVI User Manual 5-10 ni.com

Chapter 5 Performing Machine Vision Tasks

If you want to find points along a circular edge and find the circle that best fits the edge, as shown in Figure 5-6, use

imaqFindCircularEdge().

1 Annular Search Region 2 Search Lines

Figure 5-6. Finding a Circular Feature

3 Detected Edge Points 4 Circle Fit To Edge Points

Use imaqFindEdge() and imaqFindConcentricEdge() to locate the intersection points between a set of search lines within the search region and the edge of an object. You can specify the search region using

imaqSelectRect() or imaqSelectAnnulus(). Specify the separation

between the lines that the functions use to detect edges. The functions determine the intersection points based on their contrast, width, and steepness. The software calculates a best-fit line with outliers rejected or a best-fit circle through the points it found. The functions return the coordinates of the edges found.

Finding Edge Points Along One Search Contour

Use imaqSimpleEdge() or imaqEdgeTool2() to find edge points along a contour. Using edge, or all edges along the contour. Use image contains little noise and the object and background are clearly differentiated. Otherwise, use

imaqSimpleEdge(), you can find the first edge, last

imaqSimpleEdge() when your

imaqEdgeTool2().

Chapter 5 Performing Machine Vision Tasks

These functions require you to input the coordinates of the points along the search contour. Use the edge of each contour in an ROI. If you have a straight line, use

imaqGetPointsOnLine() to obtain the points along the line instead of

using an ROI.

These functions determine the edge points based on their contrast and slope. You can specify whether you want to find the edge points using subpixel accuracy.

Finding Edge Points Along Multiple Search Contours

Use imaqRake(), imaqSpoke(), and imaqConcentricRake() to find edge points along multiple search contours. These functions behave similar to

imaqEdgeTool2(), but they find edges on multiple contours. Pass in an

ROI to define the search region for these functions.

The

imaqRake() function works on a rectangular search region. The

search lines are drawn parallel to the orientation of the rectangle. Control the number of search lines in the region by specifying the distance, in pixels, between each line. Specify the search direction as left to right or right to left for a horizontally oriented rectangle. Specify the search direction as top to bottom or bottom to top for a vertically oriented rectangle.

imaqROIProfile() to obtain the coordinates along

The

imaqSpoke() function works on an annular search region, scanning

the search lines that are drawn from the center of the region to the outer boundary and that fall within the search area. Control the number of lines in the region by specifying the angle, in degrees, between each line. Specify the search direction as either going from the center outward or from the outer boundary to the center.

The

imaqConcentricRake() function works on an annular search

region. The concentric rake is an adaptation of the Rake to an annular region. IMAQ Vision does edge detection along search lines that occur in the search region and that are concentric to the outer circular boundary. Control the number of concentric search lines that are used for the edge detection by specifying the radial distance between the concentric lines in pixels. Specify the direction of the search as either clockwise or counterclockwise.

IMAQ Vision for LabWindows/CVI User Manual 5-12 ni.com

Finding Points Using Pattern Matching

The pattern matching algorithms in IMAQ Vision measure the similarity between an idealized representation of a feature, called a template, and the feature that may be present in an image. A feature is defined as a specific pattern of pixels in an image. Pattern matching returns the location of the center of the template and the template orientation. Complete the following generalized steps to find features in an image using pattern matching.

1. Define a template image in the form of a reference or fiducial pattern.

2. Use the reference pattern to train the pattern matching algorithm with

imaqLearnPattern2().

3. Define an image or an area of an image as the search area. A small search area reduces the time to find the features.

4. Set the tolerances and parameters to specify how the algorithm operates at run time using the options parameter of

imaqMatchPattern2().

5. Test the search algorithm on test images using

imaqMatchPattern2().

6. Verify the results using a ranking method.

Chapter 5 Performing Machine Vision Tasks

Defining and Creating Good Template Images

The selection of a good template image plays a critical part in obtaining good results. Because the template image represents the pattern that you want to find, make sure that all the important and unique characteristics of the pattern are well defined in the image.

These factors are critical in creating a template image: symmetry, feature detail, positional information, and background information.

Chapter 5 Performing Machine Vision Tasks

Symmetry

A rotationally symmetric template, shown in Figure 5-7a, is less sensitive to changes in rotation than one that is rotationally asymmetric, shown in Figure 5-7b. A rotationally symmetric template provides good positioning information but no orientation information.

Feature Detail

A template with relatively coarse features, shown in Figure 5-8a, is less sensitive to variations in size and rotation than a model with fine features, Figure 5-8b. However, the model must contain enough detail to identify the feature.

a. b.

Figure 5-7. Symmetry

a. b.

Figure 5-8. Feature Detail

IMAQ Vision for LabWindows/CVI User Manual 5-14 ni.com

Chapter 5 Performing Machine Vision Tasks

Positional Information

A template with strong edges in both the x and y directions is easier to locate. Figure 5-9a shows good positional information in both the x and y directions, while Figure 5-9b shows insufficient positional information in the y direction.

a. b.

Figure 5-9. Positional Information

Background Information

Unique background information in a template improves search performance and accuracy. Figure 5-10a shows a pattern with insufficient background information. Figure 5-10b illustrates a pattern with sufficient background information.

a. b.

Figure 5-10. Background Information

Training the Pattern Matching Algorithm

After you create a good template image, the pattern matching algorithm has to learn the important features of the template. Use

imaqLearnPattern2() to learn the template. The learning process

depends on the type of matching that you expect to perform. If you do not expect the instance of the template in the image to rotate or change its size, then the pattern matching algorithm has to learn only those features from

Chapter 5 Performing Machine Vision Tasks

the template that are necessary for shift-invariant matching. However, if you want to match the template at any orientation, use rotation-invariant matching. Use the learningMode parameter of to specify which type of learning mode to use.

The learning process is usually time intensive because the algorithm attempts to find the optimum features of the template for the particular matching process. The learning mode you choose also affects the speed of the learning process. Learning the template for shift-invariant matching is faster than learning for rotation-invariant matching. You can also save time by training the pattern matching algorithm offline, and then saving the template image with

Defining a Search Area

Two equally important factors define the success of a pattern matching algorithm: accuracy and speed. You can define a search area to reduce ambiguity in the search process. For example, if your image has multiple instances of a pattern and only one of them is required for the inspection task, the presence of additional instances of the pattern can produce incorrect results. To avoid this, reduce the search area so that only the desired pattern lies within the search area.

imaqLearnPattern2()

imaqWriteVisionFile().

The time required to locate a pattern in an image depends on both the template size and the search area. By reducing the search area or increasing the template size, you can reduce the required search time. Increasing the template size can improve the search time, but doing so reduces match accuracy if the larger template includes an excess of background information.

In many inspection applications, you have general information about the location of the fiducial. Use this information to define a search area. For example, in a typical component placement application, each printed circuit board (PCB) being tested may not be placed in the same location with the same orientation. The location of the PCB in various images can move and rotate within a known range of values, as illustrated in Figure 5-11. Figure 5-11a shows the template used to locate the PCB in the image. Figure 5-11b shows an image containing a PCB with a fiducial you want to locate. Notice the search area around the fiducial. If you know before the matching process begins that the PCB can shift or rotate in the image within a fixed range, then you can limit the search for the fiducial to a small region of the image. Figure 5-11c and Figure 5-11d show examples of a shifted fiducial and a rotated fiducial respectively.

IMAQ Vision for LabWindows/CVI User Manual 5-16 ni.com

Chapter 5 Performing Machine Vision Tasks

Figure 5-11. Selecting a Search Area for Grayscale Pattern Matching

Setting Matching Parameters and Tolerances

Every pattern matching algorithm makes assumptions about the images and pattern matching parameters used in machine vision applications. These assumptions work for a high percentage of the applications. However, there may be applications in which the assumptions used in the algorithm are not optimal. Knowing your particular application and the images you want to process is useful in selecting the pattern matching parameters. Use the elements that influence the IMAQ Vision pattern matching algorithm: match mode, minimum contrast, and rotation angle ranges.

Match Mode

You can set the match mode to control how the pattern matching algorithm handles the template at different orientations. If you expect the orientation of valid matches to vary less than ±5° from the template, set the element of the options parameter to Otherwise, set the mode element to

IMAQ_MATCH_ROTATION_INVARIANT.

imaqMatchPattern2() function to set the following

mode

IMAQ_MATCH_SHIFT_INVARIANT.

Note Shift-invariant matching is faster than rotation-invariant matching.

Chapter 5 Performing Machine Vision Tasks

Minimum Contrast

The pattern matching algorithm ignores all image regions in which contrast values fall below a set minimum contrast value. Contrast is the difference between the smallest and largest pixel values in a region. Set the

minContrast element of the imaqMatchPattern2() options parameter

control to slightly below the contrast value of the search area with the lowest contrast.

You can set the minimum contrast to potentially increase the speed of the pattern matching algorithm. If the search image has high contrast overall but contains some low contrast regions, set a high minimum contrast value to exclude all areas of the image with low contrast. Excluding these areas significantly reduces the area in which the pattern matching algorithm must search. However, if the search image has low contrast throughout, set a low minimum contrast to ensure that the pattern matching algorithm looks for the template in all regions of the image.

Rotation Angle Ranges

If you know that the pattern rotation is restricted to a certain range, such as between –15° to 15°, provide this restriction information to the pattern matching algorithm in the

imaqMatchPattern2() options parameter. This information improves

your search time because the pattern matching algorithm looks for the pattern at fewer angles. Refer to Chapter 12, Pattern Matching, of the IMAQ Vision Concepts Manual for information about pattern matching.

angleRanges element of the

Testing the Search Algorithm on Test Images

To determine if your selected template or reference pattern is appropriate for your machine vision application, test the template on a few test images by using images generated by your machine vision application during true operating conditions. If the pattern matching algorithm locates the reference pattern in all cases, you have selected a good template. Otherwise, refine the current template, or select a better template until both training and testing are successful.

IMAQ Vision for LabWindows/CVI User Manual 5-18 ni.com

imaqMatchPattern2(). These test images should reflect the

Using a Ranking Method to Verify Results

The manner in which you interpret the pattern matching algorithm depends on your application. For typical alignment applications, such as finding a fiducial on a wafer, the most important information is the position and location of the best match. Use the

PatternMatch structure to get the position and the bounding rectangle of

a match.

In inspection applications, such as optical character verification, the score of the best match is more useful. The score of a match returned by the pattern matching algorithm is an indicator of the closeness between the original pattern and the match found in the image. A high score indicates a very close match, while a low score indicates a poor match. The score can be used as a gauge to determine whether a printed character is acceptable. Use the

score element of the PatternMatch structure to get the score

corresponding to a match.

Finding Points Using Color Pattern Matching

Color pattern matching algorithms provide a quick way to locate objects when color is present. Use color pattern matching if your images have the following qualities:

• The object you want to locate has color information that is very different from the background, and you want to find a very precise location of the object in the image.

• The object to locate has grayscale properties that are very difficult to characterize or that are very similar to other objects in the search image. In such cases, grayscale pattern matching can give inaccurate results. If the object has color information that differentiates it from the other objects in the scene, color provides the machine vision software with the additional information to locate the object.

Chapter 5 Performing Machine Vision Tasks

position and corner elements of the

Color pattern matching returns the location of the center of the template and the template orientation. Complete the following general steps to find features in an image using color pattern matching:

1. Define a template image that contains a reference or fiducial pattern.

2. Use the reference pattern to train the color pattern matching algorithm with

imaqLearnColorPattern().

3. Define an image or an area of an image as the search area. A small search area reduces the time to find the features.

4. Set the options parameter to

featureMode element of the imaqMatchColorPattern()

IMAQ_COLOR_AND_SHAPE_FEATURES.

Chapter 5 Performing Machine Vision Tasks

5. Set the tolerances and parameters to specify how the algorithm

operates at run time using the options parameter of

imaqMatchColorPattern().

6. Test the search algorithm on test images using

imaqMatchColorPattern().

7. Verify the results using a ranking method.

Defining and Creating Good Color Template Images

The selection of a good template image plays a critical part in obtaining accurate results with the color pattern matching algorithm. Because the template image represents the color and the pattern that you want to find, make sure that all the important and unique characteristics of the pattern are well defined in the image.

Several factors are critical in creating a template image. These critical factors include color information, symmetry, feature detail, positional information, and background information. Refer to the Defining and

Creating Good Template Images section of this chapter for more

information about some of these factors.

Color Information

A template with colors that are unique to the pattern provides better results than a template that contains many colors, especially colors found in the background or other objects in the image.

Symmetry

A rotationally symmetric template in the luminance plane is less sensitive to changes in rotation than a template that is rotationally asymmetric.

Feature Detail

A template with relatively coarse features is less sensitive to variations in size and rotation than a template with fine features. However, the template must contain enough detail to identify it.

Positional Information

A template with strong edges in both the x and y directions is easier to locate.

IMAQ Vision for LabWindows/CVI User Manual 5-20 ni.com

Chapter 5 Performing Machine Vision Tasks

Background Information

Unique background information in a template improves search performance and accuracy during the grayscale pattern matching phase. This requirement could conflict with the color information requirement because background colors may not be desirable during the color location phase. Avoid this problem by choosing a template with sufficient background information for grayscale pattern matching while specifying the exclusion of the background color during the color location phase. Refer to the Training the Color Pattern Matching Algorithm section of this chapter for more information about how to ignore colors.

Training the Color Pattern Matching Algorithm

After you have created a good template image, the color pattern matching algorithm learns the important features of the template. Use

imaqLearnColorPattern() to learn the template. The learning process

depends on the type of matching that you expect to perform. By default, the color pattern matching algorithm learns only those features from the template that are necessary for shift-invariant matching. However, if you want to match the template at any orientation, the learning process must consider the possibility of arbitrary orientations. Use the element of the

imaqLearnColorPattern() options parameter to

specify which type of learning mode to use.

learnMode

Exclude colors in the template that you are not interested in using during the search phase. Typically, you should ignore colors that either belong to the background of the object or are not unique to the template, to reduce the potential for incorrect matches during the color location phase. You can ignore certain predefined colors using the

ignoreMode element of the

options parameter. To ignore other colors, first learn the colors to ignore using

imaqLearnColor(). Then set the colorsToIgnore element of the

options parameter to the resulting

imaqLearnColor().

ColorInformation structure from

The learning process is time-intensive because the algorithm attempts to find unique features of the template that allow for fast, accurate matching. However, you can train the pattern matching algorithm offline, and save the template image using

imaqWriteVisionFile().

Chapter 5 Performing Machine Vision Tasks

Defining a Search Area

Two equally important factors define the success of a color pattern matching algorithm—accuracy and speed. You can define a search area to reduce ambiguity in the search process. For example, if your image has multiple instances of a pattern and only one instance is required for the inspection task, the presence of additional instances of the pattern can produce incorrect results. To avoid this, reduce the search area so that only the desired pattern lies within the search area. For example, in the fuse box inspection example, use the location of the fuses to be inspected to define the search area. Because the inspected fuse box may not be in the exact location or have the same orientation in the image as the previous one, the search area you define must be large enough to accommodate these variations in the position of the box. Figure 5-12 shows how you can select search areas for different objects.

1 2

1 Search Area for 20 Amp Fuses 2 Search Area for 25 Amp Fuses

Figure 5-12. Selecting a Search Area for Color Pattern Matching

IMAQ Vision for LabWindows/CVI User Manual 5-22 ni.com

Chapter 5 Performing Machine Vision Tasks

Setting Matching Parameters and Tolerances

Every color pattern matching algorithm makes assumptions about the images and color pattern matching parameters used in machine vision applications. These assumptions work for a high percentage of the applications. However, there may be applications in which the assumptions used in the algorithm are not optimal. In such cases, you must modify the color pattern matching parameters. Knowing your particular application and the images you want to process is useful in selecting the pattern matching parameters. Use the options parameter of

imaqMatchColorPattern() to set these elements.

The following are elements of the IMAQ Vision pattern matching algorithm that influence color pattern matching: color sensitivity, search strategy, color score weight, ignore background colors, minimum contrast, and rotation angle ranges. These elements are discussed in the following sections.

Color Sensitivity

Use the sensitivity element to control the granularity of the color information in the template image. If the background and objects in the image contain colors that are very close to colors in the template image, use a higher color sensitivity setting. Increase the color sensitivity settings as the color differences decrease. Three color sensitivity settings are available in IMAQ Vision: and

IMAQ_SENSITIVITY_HIGH. Refer to Chapter 14, Color Inspection,

of the IMAQ Vision Concepts Manual for more information about color sensitivity.

IMAQ_SENSITIVITY_LOW, IMAQ_SENSITIVITY_MED,

Search Strategy

Use the strategy element to optimize the speed of the color pattern matching algorithm. The search strategy controls the step size, sub-sampling factor, and percentage of color information used from the template.

Chapter 5 Performing Machine Vision Tasks

Choose from the following search strategies:

•

IMAQ_CONSERVATIVE—Uses a very small step size, the least amount

of subsampling, and all the color information present in the template. The conservative strategy is the most reliable method to look for a template in any image at potentially reduced speed.

Note Use the IMAQ_CONSERVATIVE strategy if you have multiple targets located very

close to each other in the image.

•

IMAQ_BALANCED—Uses values in between the IMAQ_AGGRESSIVE

and

IMAQ_CONSERVATIVE strategies.

•

IMAQ_AGGRESSIVE—Uses a large step size, a lot of sub-sampling,

and all of the color information from the template.

•

IMAQ_VERY_AGGRESSIVE—Uses the largest step size, the most

subsampling, and only the dominant color from the template to search for the template. Use this strategy when the color in the template is almost uniform, the template is well contrasted from the background, and there is a good amount of separation between different occurrences of the template in the image. This strategy is the fastest way to find templates in an image.

Color Score Weight

When you search for a template using both color and shape information, the color and shape scores generated during the match process are combined to generate the final color pattern matching score. The color score weight determines the contribution of the color score to the final color pattern matching score. If the color information of the templates is superior to its shape information, set the weight higher. For example, if you set

colorWeight to 1000, the algorithm finds each match by using both color

and shape information, and then ranks the matches based entirely on their color scores. If you set

colorWeight to 0, the matches are still found using

color and shape information, but they are ranked based entirely on their shape scores.

Minimum Contrast

Use the minContrast element to increase the speed of the color pattern matching algorithm. The color pattern matching algorithm ignores all image regions where grayscale contrast values fall beneath a set minimum contrast value. Refer to the Setting Matching Parameters and Tolerances section of this chapter for more information about minimum contrast.

IMAQ Vision for LabWindows/CVI User Manual 5-24 ni.com

Rotation Angle Ranges

Refer to the Setting Matching Parameters and Tolerances section of this chapter for information about rotation angle ranges.

Testing the Search Algorithm on Test Images

imaqMatchColorPattern(). These test images reflect the

Finding Points Using Color Location

Color location algorithms provide a quick way to locate regions in an image with specific colors. Use color location when your application has the following characteristics:

• Requires the location and the number of regions in an image with their specific color information

• Relies on the cumulative color information in the region, instead of the color arrangement in the region

• Does not require the orientation of the region

• Does not always require the location with sub-pixel accuracy

• Does not require shape information for the region

Chapter 5 Performing Machine Vision Tasks

Complete the following general steps to find features in an image using color location.

1. Define a reference pattern in the form of a template image.

2. Use the reference pattern to train the color location algorithm with

imaqLearnColorPattern().

3. Define an image or an area of an image as the search area. A small search area reduces the time to find the features.

4. Set the options parameter to

5. Set the tolerances and parameters to specify how the algorithm operates at run time using the options parameter of

imaqMatchColorPattern().

featureMode element of the imaqMatchColorPattern()

IMAQ_COLOR_FEATURES.

Chapter 5 Performing Machine Vision Tasks

6. Test the color location algorithm on test images using

imaqMatchColorPattern().

7. Verify the results using a ranking method.

You can save the template image using

imaqWriteVisionFile().

Convert Pixel Coordinates to Real-World Coordinates

The measurement points you located with edge detection and pattern matching are in pixel coordinates. If you need to make measurements using real-world units, use the pixel coordinates into real-world units.

imaqTransformPixelToRealWorld() to convert

Make Measurements

You can make different types of measurements either directly from the image or from points that you detect in the image.

Distance Measurements

Use the following functions to make distance measurements for your inspection application.

Clamp functions measure the separation between two edges in a rectangular search region. First, clamp functions detect points along the two edges using the Rake function. Then, they compute the distance between the points detected on the edges along each search line of the rake and return the largest or smallest distance. The function generates a valid input search region for these functions. You also need to specify the parameters for edge detection and the separation between the search lines that you want to use within the search region to find the edges. These functions work directly on the image under inspection, and they output the coordinates of all the edge points that they find. The following list describes the available clamp functions:

•

imaqClampMax()—Measures the largest separation between

two edges in a rectangular search region.

•

imaqClampMin()—Finds the smallest separation between two

edges.

imaqSelectRect()

Use

imaqGetDistance() to compute the distances between two points,

such as consecutive pairs of points in an array of points. You can obtain these points from the image using any one of the feature detection methods described in the Find Measurement Points section of this chapter.

IMAQ Vision for LabWindows/CVI User Manual 5-26 ni.com

Analytic Geometry Measurements

Use the following functions to make geometrical measurements from the points you detect in the image:

•

imaqFitLine()—Fits a line to a set of points and computes the

equation of the line.

•

imaqFitCircle2()—Fits a circle to a set of at least three points and

computes its area, perimeter, and radius.

•

imaqFitEllipse2()—Fits an ellipse to a set of at least six points

and computes its area, perimeter, and the lengths of its major and minor axis.

•

imaqGetIntersection()—Finds the intersection point of two

lines specified by their start and end points.

•

imaqGetAngle()—Finds the smaller angle between two lines.

•

imaqGetPerpendicularLine()—Finds the perpendicular line

from a point to a line and computes the perpendicular distance between the point and the line.

•

imaqGetBisectingLine()—Finds the line that bisects the angle

formed by two lines.

•

imaqGetMidLine()—Finds the line that is midway between a point

and a line and is parallel to the line.

•

imaqGetPolygonArea()—Calculates the area of a polygon

specified by its vertex points.

Chapter 5 Performing Machine Vision Tasks

Instrument Reader Measurements

You can make measurements based on the values obtained by meter and LCD readers.

Use

imaqGetMeterArc() to calibrate a meter or gauge that you want to

read. The two modes. The the full-scale position of the needle. When using this mode, the function calculates the position of the base of the needle and the arc traced by the tip of the needle. The using three points on the meter: the base of the needle, the tip of the needle at its initial position, and the tip of the needle at its full-scale position. When using this mode, the function calculates the position of the points along the arc covered by the tip of the needle. Use read the position of the needle using the base of the needle and the array of points on the arc traced by the tip of the needle.

imaqGetMeterArc() function calibrates the meter using one of

IMAQ_METER_ARC_ROI mode uses the initial position and

IMAQ_METER_ARC_POINTS mode calibrates the meter

imaqReadMeter() to

Chapter 5 Performing Machine Vision Tasks

Use imaqFindLCDSegments() to calculate the ROI around each digit in an LCD or LED. To find the area of each digit, all the segments of the indicator must be activated. Use an LCD or LED.

Identify Parts Under Inspection

In addition to making measurements after you set regions of inspection, you can also identify parts using classification, optical character recognition (OCR), and barcode reading.

Classifying Samples

Use classification to identify an unknown object by comparing a set of its significant features to a set of features that conceptually represent classes of known objects. Typical applications involving classification include the following:

• Sorting—Sorts objects of varied shapes. For example, sorting different mechanical parts on a conveyor belt into different bins.

• Inspection—Inspects objects by assigning each object an identification score and then rejecting objects that do not closely match members of the training set.

imaqReadLCD() to read multiple digits of

Before you classify objects, you must train the classifier session with samples of the objects using the NI Classification Training Interface. Go to Start»Programs»National Instruments»Classification Training to launch the NI Classification Training Interface.

After you have trained samples of the objects you want to classify, use the following functions to classify the objects:

1. Use

2. Use

3. Use

IMAQ Vision for LabWindows/CVI User Manual 5-28 ni.com

imaqReadClassifierFile() to read in a classifier session that

you created using the NI Classification Training Interface.

imaqClassify() to classify the object inside the ROI of the

image under inspection into one of the classes you created using the NI Classification Training Interface.

imaqDispose() to free the resources that the classifier

session used.

Chapter 5 Performing Machine Vision Tasks

The following code sample provides an example of a typical classification application.

ClassifierSession* session;

Image* image;

ROI* roi;

char* fileName; // The classifier file to use.

ClassifierReport* report;

session = imaqReadClassifierFile(NULL, fileName,

IMAQ_CLASSIFIER_READ_ALL, NULL, NULL, NULL);

while (stillClassifying)

{

// Acquire and process an image and store it in the

//image variable.

// Locate the object to classify, and store an ROI

//containing that object in the roi variable.

report = imaqClassify(image, session, roi, NULL, 0);

// Take action based on the report.

imaqDispose(report);

}

imaqDispose(session);

Reading Characters

Use OCR to read text and/or characters in an image. Typical uses for OCR in an inspection application include identifying or classifying components.

Before you read text and/or characters in an image, you must train the OCR Session with samples of the characters using the NI OCR Training Interface. Go to Start»Programs»National Instruments»Vision»OCR Training to launch the OCR Training Interface.

After you have trained samples of the characters you want to read, use the following functions to read the characters:

1. Use

2. Use

3. Use

imaqReadOCRFile() to read in a session that you created using

the NI OCR Training Interface.

imaqReadText() to read the characters inside the ROI of the

image under inspection.

imaqDispose() to free the resources that the OCR Session used.

Chapter 5 Performing Machine Vision Tasks

Reading Barcodes

Use barcode reading functions to read values encoded into 1D barcodes, Data Matrix barcodes, and PDF417 barcodes.

Reading 1D Barcodes

To read a 1D barcode, locate the barcode in the image using one of the techniques described in this chapter. Then pass the ROI Descriptor of the location into

Use

imaqReadBarcode() to read values encoded in the 1D barcode.

Specify the type of 1D barcode in the application using the type parameter. IMAQ Vision supports the following 1D barcode types: Codabar, Code 39, Code 93, Code 128, EAN 8, EAN 13, Interleaved 2 of 5, MSI, and UPCA.

Reading Data Matrix Barcodes

Use imaqReadDataMatrixBarcode() to read values encoded in a Data Matrix barcode. The function can determine automatically the location of the barcode and appropriate search options for your application. However, you can improve the performance of the application by specifying control values specific to your application.

imaqReadBarcode().

imaqReadDataMatrixBarcode() can locate automatically one or

multiple Data Matrix barcodes in an image. However, you can improve the inspection performance by locating the barcodes using one of the techniques described in this chapter. Then pass the ROI indicating the location into

Tip If you need to read only one barcode per image, set the searchMode element of the

options parameter to

imaqReadDataMatrixBarcode().

IMAQ_SEARCH_SINGLE_CONSERVATIVE to increase the speed of

your application. If the barcode occupies a large percentage of your search region, has clearly defined cells, and exhibits little or no rotation, you can further increase the speed of your application by setting the

IMAQ_SEARCH_SINGLE_AGGRESSIVE.

By default,

searchMode element of the options parameter to

imaqReadDataMatrixBarcode() detects whether the

barcode has black cells on a white background or white cells on a black background. If the barcodes in your application have a consistent cell-to-background contrast, you can improve the performance by setting the

contrast element of the options parameter to

IMAQ_BLACK_ON_WHITE_BARCODE or IMAQ_WHITE_ON_BLACK_BARCODE.

IMAQ Vision for LabWindows/CVI User Manual 5-30 ni.com

Chapter 5 Performing Machine Vision Tasks

By default, imaqReadDataMatrixBarcode() assumes the barcode cells are square. If the barcodes you need to read have round cells, set the

cellShape element of the options parameter to IMAQ_ROUND_CELLS.

Note Specify round cells only if the Data Matrix cells are round and have clearly defined

edges. If the cells in the matrix touch one another, you must set

IMAQ_SQUARE_CELLS.

cellShape to

By default,

imaqReadDataMatrixBarcode() assumes the shape of the

barcode is square. If the shape of your barcode is rectangular, set the

barcodeShape element of the options parameter to IMAQ_RECTANGULAR_BARCODE_2D.

Note Setting the barcodeShape element to IMAQ_RECTANGULAR_BARCODE_2D when

the barcode you need to read is square reduces the reliability of your application.

By default,

imaqReadDataMatrixBarcode() automatically detects the

type of barcode to read. You can improve the performance of the your function by specifying the type of barcode in your application. IMAQ Vision supports Data Matrix types ECC 000 to ECC 140, and ECC 200.

Reading PDF417 Barcodes

Use imaqReadPDF417Barcode() to read values encoded in a PDF417 barcode.

imaqReadPDF417Barcode() can locate automatically one or multiple

PDF417 barcodes in an image. However, you can improve the inspection performance by locating the barcodes using one of the techniques described in this chapter. Then pass in the ROI location to

imaqReadPDF417Barcode().

Tip If you need to read only one barcode per image, set the searchMode parameter to

IMAQ_SEARCH_SINGLE_CONSERVATIVE to increase the speed of your application.

Display Results

You can overlay the results obtained at various stages of you inspection process on the window that displays your inspection image. The software attaches the information that you want to overlay to the image, but it does not modify the image. The overlay appears every time you display the image in an external window.

Chapter 5 Performing Machine Vision Tasks

Use the following functions to overlay search regions, inspection results, and other information, such as text and bitmaps.

•

imaqOverlayPoints()—Overlays points on an image. Specify a

point by its x-coordinate and y-coordinate.

•

imaqOverlayLine()—Overlays a line on an image. Specify a line

by its start and end points.

•

imaqOverlayRect()—Overlays a rectangle on an image.

•

imaqOverlayOval()—Overlays an oval or a circle on the image.

•

imaqOverlayArc()—Overlays an arc on the image.

•

imaqOverlayMetafile()—Overlays a metafile on the image.

•

imaqOverlayText()—Overlays text on an image.

•

imaqOverlayROI()—Overlays an ROI on an image.

•

imaqOverlayClosedContour()—Overlays a closed contour on an

image.

•

imaqOverlayOpenContour()—Overlays an open contour on an

image.

To use these functions, pass in the image on which you want to overlay information and the information that you want to overlay.

Tip You can select the color of overlays with these functions.

You can configure the following processing functions to overlay different types of information on the inspection image:

• imaqFindEdge()

• imaqFindCircularEdge()

• imaqFindConcentricEdge()

• imaqClampMax()

• imaqClampMin()

• imaqFindPattern()

• imaqCountObjects()

• imaqFindTransformRect()

• imaqFindTransformRects()

• imaqFindTransformPattern()

IMAQ Vision for LabWindows/CVI User Manual 5-32 ni.com

Chapter 5 Performing Machine Vision Tasks

The following list contains the kinds of information you can overlay with the previous functions except

imaqCountObjects(), and imaqFindTransformPattern().

imaqFindPattern(),

• The search area input into the function

• The search lines used for edge detection

• The edges detected along the search lines

• The result of the function

With

imaqFindPattern(), imaqCountObjects(), and

imaqFindTransformPattern()

, you can overlay the search area and the result. Select the information you want to overlay by setting the element that corresponds to the information type to

TRUE in the options input

parameter.

Use

imaqClearOverlay() to clear any previous overlay information

from the image. Use

imaqWriteVisionFile() to save an image with

its overlay information to a file. You can read the information from the file into an image using

Note As with calibration information, overlay information is removed from an image

imaqReadVisionFile().

when the image size or orientation changes.

Calibrating Images

This chapter describes how to calibrate your imaging system, save calibration information, and attach calibration information to an image.

After you set up your imaging system, you may want to calibrate your system. If your imaging setup is such that the camera axis is perpendicular or nearly perpendicular to the object under inspection and your lens has no distortion, use simple calibration. With simple calibration, you do not need to learn a template. Instead, you define the distance between pixels in the horizontal and vertical directions using real-world units.

If your camera axis is not perpendicular to the object under inspection, use perspective calibration to calibrate your system. If your lens is distorted, use nonlinear distortion calibration.

Perspective and Nonlinear Distortion Calibration

Perspective errors and lens aberrations cause images to appear distorted. This distortion misplaces information in an image, but it does not necessarily destroy the information in the image. Calibrate your imaging system if you need to compensate for perspective errors or nonlinear lens distortion.

Complete the following general steps to calibrate your imaging system:

1. Define a calibration template.

2. Define a reference coordinate system.

3. Learn the calibration information.

After you calibrate your imaging system, you can attach the calibration information to an image. Refer to the Attach Calibration Information section of this chapter for more information. Then, depending on your needs, you can do one of the following:

• Use the calibration information to convert pixel coordinates to

real-world coordinates without correcting the image.

• Create a distortion-free image by correcting the image for perspective

errors and lens aberrations.

Chapter 6 Calibrating Images

Refer to Chapter 5, Performing Machine Vision Tasks, for more information about applying calibration information before making measurements.

Defining a Calibration Template

You can define a calibration template by supplying an image of a grid or providing a list of pixel coordinates and their corresponding real-world coordinates. This section discusses the grid method in detail.

A calibration template is a user-defined grid of circular dots. As shown in Figure 6-1, the grid has constant spacings in the x and y directions. You can use any grid, but follow these guidelines for best results:

• The displacement in the x and y directions should be equal (dx = dy).

• The dots should cover the entire desired working area.

• The radius of the dots in the acquired image should be 6–10 pixels.

• The center-to-center distance between dots in the acquired image should range from 18 to 32 pixels, as shown in Figure 6-1.

• The minimum distance between the edges of the dots in the acquired image should be 6 pixels, as shown in Figure 6-1.

1 Center-to-Center Distance 2 Center of Grid Dots 3 Distance Between Dot Edges

Figure 6-1. Defining a Calibration Grid

Note

Click Start»Programs»National Instruments»Vision»Documentation»

Calibration Grid to use the calibration grid installed with IMAQ Vision. The dots have radii of 2 mm and center-to-center distances of 1 cm. Depending on your printer, these measurements may change by a fraction of a millimeter. You can purchase highly accurate calibration grids from optics suppliers, such as Edmund Industrial Optics.

IMAQ Vision for LabWindows/CVI User Manual 6-2 ni.com

Defining a Reference Coordinate System

To express measurements in real-world units, you need to define a coordinate system in the image of the grid. Use the structure to define a coordinate system by its origin, angle, and axis direction.

The origin, expressed in pixels, defines the center of your coordinate system. The angle specifies the orientation of your coordinate system with respect to the angle of the topmost row of dots in the grid image. The calibration procedure automatically determines the direction of the horizontal axis in the real world. The vertical axis direction can either be indirect, as shown in Figure 6-2a, or direct, as shown in Figure 6-2b.

Chapter 6 Calibrating Images

CoordinateSystem

a. b.

Figure 6-2. Axis Direction in the Image Plane

If you do not specify a coordinate system, the calibration process defines a default coordinate system. If you specify a grid for the calibration process, the software defines the following default coordinate system, as shown in Figure 6-3:

1. The origin is placed at the center of the left, topmost dot in the calibration grid.

2. The angle is set to 0°. This aligns the x-axis with the first row of dots in the grid, as shown in Figure 6-3b.

3. The axis direction is set to indirect. This aligns the y-axis to the first column of the dots in the grid, as shown in Figure 6-3b.

Chapter 6 Calibrating Images

1 Origin of a Calibration Grid in the Real World 2 Origin of the Same Calibration Grid in an Image

Figure 6-3. A Calibration Grid and an Image of the Grid

If you specify a list of points instead of a grid for the calibration process,

Note

the software defines a default coordinate system, as follows:

1. The origin is placed at the point in the list with the lowest x-coordinate value and then the lowest y-coordinate value.

2. The angle is set to 0°.

3. The axis direction is set to indirect.

If you define a coordinate system yourself, carefully consider the needs of your application.

• Express the origin in pixels. Always choose an origin location that lies within the calibration grid so that you can convert the location to real-world units.

• Specify the angle as the angle between the x-axis of the new coordinate system (x') and the top row of dots (x), as shown in Figure 6-4. If your imaging system exhibits nonlinear distortion, you cannot visualize the angle as you can in Figure 6-4 because the dots do not appear in straight lines.

IMAQ Vision for LabWindows/CVI User Manual 6-4 ni.com

Chapter 6 Calibrating Images

1 Default Origin in a Calibration Grid Image 2 User-Defined Origin

Learning Calibration Information

After you define a calibration grid and reference axis, acquire an image of the grid using the current imaging setup. For information about acquiring images, refer to the Acquire or Read an Image section of Chapter 2, Getting

Measurement-Ready Images. The grid does not need to occupy the entire

image. You can choose a region within the image that contains the grid. After you acquire an image of the grid, learn the calibration information by inputting the image of the grid into

Note If you want to specify a list of points instead of a grid, use

imaqLearnCalibrationPoints() to learn the calibration information. Use the CalibrationPoints structure to specify the pixel to real-world mapping.

Figure 6-4. Defining a Coordinate System

imaqLearnCalibrationGrid().

Chapter 6 Calibrating Images

Note The user-defined ROI represents the area in which you are interested. The learning

ROI is different from the calibration ROI generated by the calibration algorithm. Refer to Figure 6-6 for an illustration of calibration ROIs.

Specifying Scaling Factors

Scaling factors are the real-world distances between the dots in the calibration grid in the x and y directions and the units in which the distances are measured. Use the factors.

GridDescriptor structure to specify the scaling

Choosing a Region of Interest

Define a learning ROI during the learning process to define a region of the calibration grid you want to learn. The software ignores dot centers outside this region when it estimates the transformation. Depending on the other calibration options selected, this is an effective way to increase correction speeds. Set the user-defined ROI using the roi parameter of either

imaqLearnCalibrationGrid() or imaqLearnCalibrationPoints().

Choosing a Learning Algorithm

Select a method in which to learn the calibration information: perspective projection or nonlinear. Figure 6-5 illustrates the types of errors your image can exhibit. Figure 6-5a shows an image of a calibration grid with no errors. Figure 6-5b shows an image of a calibration grid with perspective projection. Figure 6-5c shows an image of a calibration grid with nonlinear distortion.

a. c.b.

Figure 6-5. Types of Image Distortion

IMAQ Vision for LabWindows/CVI User Manual 6-6 ni.com

Chapter 6 Calibrating Images

Choose the perspective projection algorithm when your system exhibits perspective errors only. A perspective projection calibration has an accurate transformation even in areas not covered by the calibration grid, as shown in Figure 6-6. Set the

IMAQ_PERSPECTIVE to choose the perspective calibration algorithm.

mode element of the options parameter to

Learning and applying perspective projection is less computationally intensive than the nonlinear method. However, perspective projection cannot handle nonlinear distortions.

If your imaging setup exhibits nonlinear distortion, use the nonlinear method. The nonlinear method guarantees accurate results only in the area that the calibration grid covers, as shown in Figure 6-6. If your system exhibits both perspective and nonlinear distortion, use the nonlinear method to correct for both. Set the to

IMAQ_NONLINEAR to choose the nonlinear calibration algorithm.

mode element of the options parameter

1 Calibration ROI Using the Perspective Algorithm 2 Calibration ROI Using the Nonlinear Algorithm

Figure 6-6. Calibration ROIs

Using the Learning Score

The learning process returns a score that reflects how well the software learned the input image. A learning score above 800 indicates that you chose the appropriate learning algorithm, that the grid image complies with the guideline, and that your vision system setup is adequate.

Note A high score does not reflect the accuracy of your system.

Chapter 6 Calibrating Images

If the learning process returns a learning score below 600, try the following:

1. Make sure your grid complies with the guidelines listed in the

Defining a Calibration Template section of this chapter.

2. Check the lighting conditions. If you have too much or too little lighting, the software may estimate the center of the dots incorrectly. Also, adjust the range parameter to distinguish the dots from the background.

3. Select another learning algorithm. When nonlinear lens distortion is present, using perspective projection sometimes results in a low learning score.

Learning the Error Map

An error map helps you gauge the quality of your complete system. The error map returns an estimated error range to expect when a pixel coordinate is transformed into a real-world coordinate. The transformation accuracy may be higher than the value the error range indicates. Set the

learnMap element of the options parameter to TRUE to learn the error

map.

Learning the Correction Table

If the speed of image correction is a critical factor for your application, use a correction table. The correction table is a lookup table stored in memory that contains the real-world location information of all the pixels in the image. The extra memory requirements for this option are based on the size of the image. Use this option when you want to correct several images at a time in your vision application. Set the options parameter to

TRUE to learn the correction table.

learnTable element of the

Setting the Scaling Method

Use the method element of the options parameter to choose the appearance of the corrected image. Select either

IMAQ_SCALE_TO_PRESERVE_AREA. Refer to Chapter 3, System Setup and

Calibration, of the IMAQ Vision Concepts Manual for more information

about the scaling methods.

IMAQ_SCALE_TO_FIT or

Calibration Invalidation

Any image processing operation that changes the image size or orientation voids the calibration information in a calibrated image. Examples of functions that void calibration information include

imaqScale(), imaqArrayToImage(), and imaqUnwrap().

IMAQ Vision for LabWindows/CVI User Manual 6-8 ni.com

imaqResample(),

Simple Calibration

When the axis of your camera is perpendicular to the image plane and lens distortion is negligible, use simple calibration. In simple calibration, a pixel coordinate is transformed to a real-world coordinate through scaling in the horizontal and vertical directions.

Use simple calibration to map pixel coordinates to real-world coordinates directly without a calibration grid. The software rotates and scales a pixel coordinate according to predefined coordinate reference and scaling factors. You can assign the calibration to an arbitrary image using

imaqSetSimpleCalibration().

To perform a simple calibration, set a coordinate reference (angle, center, and axis direction) and scaling factors on the defined axis, as shown in Figure 6-7. Express the angle between the x-axis and the horizontal axis of the image in degrees. Express the center as the position, in pixels, where you want the coordinate reference origin. Set the axis direction to direct or indirect. Simple calibration also offers a correction table option and a scaling mode option.

Use the system parameter to define the coordinate system. Use the grid parameter to specify the scaling factors. Use the method parameter to set the scaling method. Set the learnTable parameter to correction table.

Chapter 6 Calibrating Images

TRUE to learn the

1Origin

Figure 6-7. Defining a Simple Calibration

Chapter 6 Calibrating Images

Save Calibration Information

After you learn the calibration information, you can save it so that you do not have to relearn the information for subsequent processing. Use

imaqWriteVisionFile() to save the image of the grid and its associated

calibration information to a file. To read the file containing the calibration information use Calibration Information section of this chapter for more information about attaching the calibration information you read from another image.

imaqReadVisionFile(). Refer to the Attach

Attach Calibration Information

Now that you have calibrated your setup correctly, you can apply the calibration settings to images that you acquire. Use

imaqCopyCalibrationInfo() to attach the calibration information of

the current setup to each image you acquire. This function takes in a source image containing the calibration information and a destination image that you want to calibrate. The destination image is your inspection image with the calibration information attached to it.

Using the calibration information attached to the image, you can accurately convert pixel coordinates to real-world coordinates to make any of the analytic geometry measurements with

imaqTransformPixelToRealWorld(). If your application requires that

you make shape measurements, correct the image by removing distortion with

imaqCorrectImage().

Note Correcting images is a time-intensive operation.

A calibrated image is not the same as a corrected image. Because calibration information is part of the image, it is propagated throughout the processing and analysis of the image. Functions that modify the image size, such as an image rotation function, void the calibration information. Use

imaqWriteVisionFile() to save the image and all of the attached

calibration information to a file.

IMAQ Vision for LabWindows/CVI User Manual 6-10 ni.com

Technical Support and Professional Services

Visit the following sections of the National Instruments Web site at

ni.com for technical support and professional services:

• Support—Online technical support resources at

include the following:

– Self-Help Resources—For immediate answers and solutions,

visit the award-winning National Instruments Web site for software drivers and updates, a searchable KnowledgeBase, product manuals, step-by-step troubleshooting wizards, thousands of example programs, tutorials, application notes, instrument drivers, and so on.

– Free Technical Support—All registered users receive free Basic

Service, which includes access to hundreds of Application Engineers worldwide in the NI Developer Exchange at

ni.com/exchange. National Instruments Application Engineers

make sure every question receives an answer.

• Training and Certification—Visit

self-paced training, eLearning virtual classrooms, interactive CDs, and Certification program information. You also can register for instructor-led, hands-on courses at locations around the world.

• System Integration—If you have time constraints, limited in-house

technical resources, or other project challenges, National Instruments Alliance Partner members can help. To learn more, call your local NI office or visit

ni.com/alliance.

ni.com/support

ni.com/training for

If you searched your local office or NI corporate headquarters. Phone numbers for our worldwide offices are listed at the front of this manual. You also can visit the Worldwide Offices section of office Web sites, which provide up-to-date contact information, support phone numbers, email addresses, and current events.

ni.com and could not find the answers you need, contact

ni.com/niglobal to access the branch

Glossary

Numbers

1D One-dimensional.

2D Two-dimensional.

3D Three-dimensional.

AIPD The National Instruments internal image file format used for saving

complex images and calibration information associated with an image (extension APD).

alignment The process by which a machine vision application determines the

location, orientation, and scale of a part being inspected.

alpha channel The channel used to code extra information, such as gamma correction,

about a color image. The alpha channel is stored as the first byte in the four-byte representation of an RGB pixel.

area (1) A rectangular portion of an acquisition window or frame that is

controlled and defined by software.

(2) The size of an object in pixels or user-defined units.

arithmetic operators The image operations multiply, divide, add, subtract, and modulo.

array An ordered, indexed set of data elements of the same type.

auto-median function A function that uses dual combinations of opening and closing operations

to smooth the boundaries of objects.

b Bit. One binary digit, either 0 or 1.

B Byte. Eight related bits of data, an eight-bit binary number. Also denotes

the amount of memory required to store one byte of data.

Glossary

barycenter The grayscale value representing the centroid of the range of an image’s

grayscale values in the image histogram.

binary image An image in which the objects usually have a pixel intensity of 1 (or 255)

and the background has a pixel intensity of 0.

binary morphology Functions that perform morphological operations on a binary image.

binary threshold The separation of an image into objects of interest (assigned a pixel value

of 1) and background (assigned pixel values of 0) based on the intensities of the image pixels.

bit depth The number of bits (n) used to encode the value of a pixel. For a given n,

a pixel can take 2

different values. For example, if n equals 8, a pixel can take 256 different values ranging from 0 to 255. If n equals 16, a pixel can take 65,536 different values ranging from 0 to 65,535 or –32,768 to 32,767.

blurring Reduces the amount of detail in an image. Blurring commonly occurs

because the camera is out of focus. You can blur an image intentionally by applying a lowpass frequency filter.

BMP Bitmap. An image file format commonly used for 8-bit and color images.

BMP images have the file extension BMP.

border function Removes objects (or particles) in a binary image that touch the image

border.

brightness (1) A constant added to the red, green, and blue components of a color pixel

during the color decoding process.

(2) The perception by which white objects are distinguished from gray and light objects from dark objects.

buffer Temporary storage for acquired data.

IMAQ Vision for LabWindows/CVI User Manual G-2 ni.com

Glossary

caliper (1) A function in the NI Vision Assistant and in NI Vision Builder for

Automated Inspection that calculates distances, angles, circular fits, and the center of mass based on positions given by edge detection, particle analysis, centroid, and search functions.

(2) A measurement function that finds edge pairs along a specified path in the image. This function performs an edge extraction and then finds edge pairs based on specified criteria such as the distance between the leading and trailing edges, edge contrasts, and so forth.

center of mass The point on an object where all the mass of the object could be

concentrated without changing the first moment of the object about any axis.

chroma The color information in a video signal.

chromaticity The combination of hue and saturation. The relationship between

chromaticity and brightness characterizes a color.

closing A dilation followed by an erosion. A closing fills small holes in objects and

smooths the boundaries of objects.

clustering A technique where the image is sorted within a discrete number of classes

corresponding to the number of phases perceived in an image. The gray values and a barycenter are determined for each class. This process is repeated until a value is obtained that represents the center of mass for each phase or class.

CLUT Color lookup table. A table for converting the value of a pixel in an image

into a red, green, and blue (RGB) intensity.

color image An image containing color information, usually encoded in the RGB form.

color space The mathematical representation for a color. For example, color can be

described in terms of red, green, and blue; hue, saturation, and luminance; or hue, saturation, and intensity.

complex image Stores information obtained from the FFT of an image. The complex

numbers that compose the FFT plane are encoded in 64-bit floating-point values: 32 bits for the real part and 32 bits for the imaginary part.

connectivity Defines which of the surrounding pixels of a given pixel constitute its

neighborhood.

Glossary

connectivity-4 Only pixels adjacent in the horizontal and vertical directions are considered

neighbors.

connectivity-8 All adjacent pixels are considered neighbors.

contrast A constant multiplication factor applied to the luma and chroma

components of a color pixel in the color decoding process.

convex hull The smallest convex polygon that can encapsulate a particle.

convex hull function Computes the convex hull of objects in a binary image.

convolution See linear filter.

convolution kernel 2D matrices, or templates, used to represent the filter in the filtering

process. The contents of these kernels are a discrete two-dimensional representation of the impulse response of the filter that they represent.

Danielsson function Similar to the distance functions, but with more accurate results.

determinism

digital image An image f (x, y) that has been converted into a discrete number of pixels.

dilation Increases the size of an object along its boundary and removes tiny holes in

driver Software that controls a specific hardware device, such as an IMAQ or

A characteristic of a system that describes how consistently it can respond to external events or perform operations within a given time limit.

Both spatial coordinates and brightness are specified.

the object.

DAQ device.

edge Defined by a sharp transition in the pixel intensities in an image or along

an array of pixels.

edge contrast The difference between the average pixel intensity before and the average

pixel intensity after the edge.

edge detection Any of several techniques to identify the edges of objects in an image.

IMAQ Vision for LabWindows/CVI User Manual G-4 ni.com

National Instruments IMAQ Vision for LabWindows TM CVI User Manual

Specifications and Main Features

Frequently Asked Questions

User Manual

IMAQ Vision for LabWindows/CVI User Manual

Support

Worldwide Technical Support and Product Information

National Instruments Corporate Headquarters

Worldwide Offices

Important Information

Warranty

Copyright

Trademarks

Patents

WARNING REGARDING USE OF NATIONAL INSTRUMENTS PRODUCTS

Contents

About This Manual

Conventions

Related Documentation

IMAQ Vision

NI Vision Assistant

NI Vision Builder for Automated Inspection

Other Documentation

About IMAQ Vision

Application Development Environments

IMAQ Vision Function Tree

Table 1-1. IMAQ Vision Function Types

IMAQ Machine Vision Function Tree

Table 1-2. IMAQ Machine Vision Function Types

Creating IMAQ Vision Applications

Figure 1-1. General Steps for Designing a Vision Application

Figure 1-2. Inspection Steps for Building a Vision Application

Set Up Your Imaging System

Calibrate Your Imaging System

Create an Image

Table 2-1. IMAQ Vision for LabWindows/CVI Image Types

Source and Destination Images

Acquire or Read an Image

Acquiring an Image

Reading a File

Converting an Array to an Image

Display an Image

Attach Calibration Information

Analyze an Image

Improve an Image

Lookup Tables

Filters

Convolution Filter

Nth Order Filter

Grayscale Morphology

Complex Image Operations

Define Regions of Interest

Figure 3-1. Steps to Taking Grayscale and Color Measurements

Defining Regions Interactively

Table 3-1. Tools Palette Functions

Figure 3-2. ROI Constructor

Tools Palette Transformation

Figure 3-3. Tools Palette Tools and Information

Defining Regions Programmatically

Defining Regions with Masks

Measure Grayscale Statistics

Measure Color Statistics

Figure 3-4. Primary Components of a 32-Bit Color Image

Figure 3-5. Primary Components of a 64-Bit Color Image

Comparing Colors

Learning Color Information

Specifying the Color Information to Learn

Figure 3-6. Template Color Information

Figure 3-7. Using the Entire Image to Learn Color Distribution

Figure 3-8. Using a Single Region to Learn Color Distribution

Figure 3-9. Using Multiple Regions to Learn Color Distribution

Choosing a Color Representation Sensitivity

Ignoring Learned Colors

Create a Binary Image

Figure 4-1. Steps to Performing Particle Analysis

Improve the Binary Image

Removing Unwanted Particles

Separating Touching Particles

Improving Particle Shapes

Make Particle Measurements