Automatic segmentation of boundaries in line segments and circular arcs

Abstract

An evaluation function is presented, which tests the results of an object boundary segmentation algorithm to choose an optimal approximation using lines and circular arcs. An angle detection procedure is used to find sharp corners of the object boundary. Because this procedure does not detect smooth changes, the boundary segments defined by the sharp corners are further processed with a Gauss-filter-based method to find the possibly remaining connection points. Between these points and the sharp corners the boundary is approximated by means of lines or circular arcs. Because the processing steps have different control parameters, different parameter sets are automatically tested. Using a function which evaluates the precision, length, and quantity of line segments and circular arcs, an optimal segmentation is chosen.