Справочник Пользователя для National Instruments IMAQTM
Chapter 5
Performing Machine Vision Tasks
© National Instruments Corporation
5-15
Background Information
Unique background information in a template improves search
performance and accuracy.
performance and accuracy.
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
algorithm has to learn the important features of the template. Use
CWIMAQVision.LearnPattern2
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, the pattern matching algorithm has to learn 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 mode
must consider the possibility of arbitrary orientations. To specify
which type of learning mode to use, pass the learn mode to
the
do not expect the instance of the template in the image to rotate or change
its size, the pattern matching algorithm has to learn 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 mode
must consider the possibility of arbitrary orientations. To specify
which type of learning mode to use, pass the learn mode to
the
LearnPatternOptions
parameter of
CWIMAQVision.LearnPattern2
. You also can set the
LearnMode
property of a CWIMAQLearnPatternOptions object and pass this object
for the
for the
LearnPatternOptions
parameter of
CWIMAQVision.LearnPattern2
.
The learning process is usually time intensive because the algorithm
attempts to find unique features of the template that allow for fast, accurate
matching. 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 also can save time
by training the pattern matching algorithm offline, and then saving the
template image with
attempts to find unique features of the template that allow for fast, accurate
matching. 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 also can save time
by training the pattern matching algorithm offline, and then saving the
template image with
CWIMAQVision.WriteImageAndVisionInfo
.
a
Pattern with Insufficient Background Information
b
Pattern with Sufficient Background Information
a.
b.