Аннотация:The task of binary classification (recognition) of reference micromarks images and background
surface relief around micromarks, obtained during the micromarks searching using a probe microscope, is
considered. Typical images of markings consisting of linear segments oriented orthogonal to each other are
presented. The possibilities of conventional processing methods for recognizing markings in images have
been analyzed. A classification algorithm based on erosion morphological operation, threshold filtering, and
Hough transform is described. The classification has been performed using structural analysis of the Hough
transform results, configured to search for straight-line segments. Metrics for evaluating the efficiency of the
proposed solutions are given.