Image segmentation via contour tracking in application to the analysis of the photographs of electronic microcircuits
Pavel A. Chochia · Journal of Communications Technology and Electronics · 2010
An algorithm for segmentation of the photographs of microcircuits obtained with an electron microscope is considered. The images are characterized by a high level of noise and the presence of two different types of boundaries between the observed objects. Segmentation is performed by contour tracking at the boundaries between patterns. Detection of the first-type boundaries, transformation of the second-type boundaries into the first-type boundaries, and final contour tracking in the combined synthesized image are realized. The problem of the removal of false contour lines and segments is discussed.