Machine Vision
Matching / Part Location
Matching is one of the most used algorithms in image processing: a golden sample is taught and every produced part is compared against it.

The basic idea is to teach the original image (usually a specific region) and search for it in subsequent images: comparing produced parts against a golden sample, in industrial terms. Matching is used in nearly every area of machine vision: measurement, defect detection, completeness, print monitoring, positioning, orientation, 3D and robotics.
Shape-based matching works even when the part is rotated, scaled or partially occluded. It delivers results in milliseconds to separate mixed product types on a conveyor or verify that the right product goes into the right box.
Highlights
- Shape-based, rotation tolerant
- Millisecond results
- Product type sorting
- Orientation and position finding
Application areas
- Packaging
- Electronics
- Automotive
- Food

