Start » Filter Reference » Computer Vision » Image Analysis » CompareGoldenTemplate_Intensity

CompareGoldenTemplate_Intensity

Basic

Module: FoundationPro

Compares an image with a template image considered to have no defects.

Applications

Finding general object defects by analyzing brightness deviations from a template image.
Name Type Range Description
Input value
 inImage Image Input image
Input value
 inGoldenTemplate GrayGoldenTemplate Golden gray template containing image of an object with no defects
Input value
 inGoldenTemplateAlignment CoordinateSystem2D* Adjusts the golden template to the position of the inspected object
Input value
 inMaxDifference Real 0.0 - Maximal allowed difference between corresponding pixels of the input and golden images
Input value
 inMinDefectRadius Integer 0 - Minimal radius of a defect
Output value
 outDefects Region Region of detected defects
Output value
 outDifferenceRegion Region Region of pixels differing too much between the golden image and the input image
Output value
 outDefectsPresent Bool Flag indicating whether any defects were detected
Output value
 outEdgeRegion Region Region of pixels that will not be compared
Output value
 outObjectPosition Rectangle2D Position of the object being compared

Description

This filter compares pixels of the input images against a template image stored in passed inGoldenTemplate input. Then creates a region containing only pixels in which intensity difference is higher than inMaxDifference value as a result. This method is especially useful for finding defects like: smudges, noises and dust particles. It can be used for finding missing holes or changes in complex shapes.

When the defected pixels are found only consistent regions are selected. Minimal radius of accepted region is set in inMinDefectRadius.

You can define a part of an image when defining inGoldenTemplate.

More information about this technique can be found in Machine Vision Guide: Golden Template.

Hints

  • A golden template comparison filter should be preceded with filters finding the object in certain location. Most typically we do this with LocateSingleObject_Edges1 filter.
  • Connect the inImage input with the image containing the object.
  • Select an image with a perfect object and use it to create golden template using the CreateGoldenTemplate_Intensity filter.
  • Set inMaxDifference to a value that assures detection of all true defects and no false ones. Verify this with the outDefects output.
  • Dismiss very small defects by setting inMinDefectRadius.

Examples

CompareGoldenTemplate_Intensity performed on sample image. A part of the object is missing – it is marked in blue on the right.

Remarks

Due to performance, it is recommended to create a template using the CreateGoldenTemplate_Intensity filter outside a main loop of a program. It will create a model only once, instead of each iteration.

Errors

This filter can throw an exception to report error. Read how to deal with errors in Error Handling.

List of possible exceptions:

Error type Description
DomainError Input image format is incompatible with golden template image format in CompareGoldenTemplate_Intensity.
DomainError No valid golden template on input in CompareGoldenTemplate_Intensity.

Complexity Level

This filter is available on Basic Complexity Level.

Filter Group

This filter is member of CompareGoldenTemplate filter group.

See Also

  • CompareGoldenTemplate_Edges – Compares image edges with the edges of a perfect template. Significant differences are considered defects.