National Instruments IMAQTM 用户手册

© National Instruments Corporation

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. For information about coordinate systems, refer to 
Chapter 13, Dimensional Measurements, of the IMAQ Vision Concepts 
Manual.

You can build a coordinate transformation using edge detection or 
pattern matching. The output of the edge detection and pattern 
matching methods that build a coordinate transformation is a 
CWMVCoordinateTransformation object, which contains a reference 
coordinate system and a measurement coordinate system. Some machine 
vision methods take this transformation and adjust the regions of inspection 
automatically. You also can use these outputs to move the regions of 
inspection relative to the object programmatically.

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

CWMachineVision.FindCoordTransformUsingRect

 

to define a reference coordinate system using one rectangular region. Use 

CWMachineVision.FindCoordTransformUsingTwoRects

 to define a 

reference coordinate system using two independent rectangular regions. 
Follow the steps below to build a coordinate transformation using edge 
detection.

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 

CWMachineVision.FindCoordTransformUsingRect

, 

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.