From the Feature Type drop-down list, select Pattern.
Click 
, the Pattern tab opens.
Click 
to set the train region over the pattern that you will use as the training model. Ensure that the train region covers only the feature of the pattern.
Click 
on the right top corner of the display to confirm the train region.
The 
icon replaces the train region, which indicates the location and angular orientation of the found pattern.
(Optional) Click 
to set the search region. Ensure that search region covers the areas in the image where you expect to see the pattern. By default, the search region covers the entire field of view.
Click on the right top corner of the display to confirm the search region.
After you configure the pattern settings, load images and adjust the parameters, as necessary, to compensate for your expected ranges of variations.
| Parameters | Description |
| Contrast Threshold |
Specifies the lowest contrast of a valid instance. The contrast for a potential match must be greater than the value of the Contrast Threshold or that instance will not be considered (0 to 100; default = 15). |
| Angle Range | Specifies the search tolerance to the pattern rotation (0 to 180; default = 20). |
| Accept Threshold | Specifies the minimum acceptable pattern response score (0 to 100; default = 60). |
| Nominal Scale |
Specifies the nominal scale value of the image (50 to 150; default = 100). You use this parameter to adjust the scale difference between the rumtime image and the trained image. For example, if the runtime image size is only 80% of the trained image, the Nominal Scale value should be set to 80. |
| Clutter in Score |
Specifies whether extra features will reduce the response score(s). By default, this check box is not selected. |
Example
Click to exit the Recipe step. The sensor is now set up and ready for the sensor calibration.