Pattern recognition on metal surface

To measure deformations of metal material under a loading, it is usual that the material surface patterns are recognized first by using image technique. Normally, the surface patterns consist of a number of parametric graphic elements such as circle, ellipse, square and rectangle. To successfully applying automatic image processing techniques for the problem of automatic pattern detection and description, the hardest task is the automatic detection of patterns robustly in images. A so-called valley-edge detection algorithm ("valley" or ("ridge") means here finding locally dark (or bright) line-like features) is one-pass line detection algorithm (without thresholding step). The developed pattern detection algorithm is the robust for ridge edge detection and line tracing. The algorithm has been tested, and the results indicate that this approach is useful in this kind of domains of images.