New polygonal approximation schemes for object shape representation

Abstract

Object shape representation is an important issue in pattern recognition and computer vision applications. A set of new polygonal approximation schemes, namely, the internal maximum area polygonal approximation (IMAPA), the external minimum area polygonal approximation (EMAPA), and the minimum area deviation polygonal approximation (MADPA), are proposed for object shape representation. The area deviation between the initial object shape and its approximation polygon is defined as the cost function. Instead of outputting a unique approximation polygon, each proposed scheme outputs a sequence of approximation polygons with different numbers of line segments and different area deviations for various application situations. For a given area deviation bound and an initial object shape, each proposed scheme can give a corresponding “optimal” approximation polygon with a minimum number of line segments. A performance comparison among the proposed schemes is included. The proposed schemes are compared with two other existing schemes. Some experimental results show the feasibility of the proposed approaches.