Справочник Пользователя для National Instruments IMAQ Vision for LabWindows TM /CVI

© National Instruments Corporation

Refer to the 

 section of this 

chapter for information about rotation angle ranges.

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 

imaqMatchColorPattern()

. These test images reflect the 

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.

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

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 

featureMode

 element of the 

imaqMatchColorPattern()

 

options parameter to 

IMAQ_COLOR_FEATURES

.

5.

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

imaqMatchColorPattern()

.