AN OPTIMIZATION APPROACH TO SHAPE-MATCHING AND RECOGNITION

An optimization approach to shape matching and recognition is presente d. The technique is a vertex based technique that uses surface contact as a criterion for measuring similarity. Given an object (polygon O) and a reference template (polygon T), the feasible region generated by polygon T is continuously magnified (expanded or contracted) by a fac tor, epsilon, and polygon O is translated and rotated such that it fal ls inside T. The objective is to minimize the magnification factor. Th e problem is formulated as a nonlinear optimization problem with a lin ear objective function and nonlinear constraints. A search-based proce dure is used to solve this problem. To ensure global optimality, the n onlinear constraints are replaced by their linear approximations.The r esults show that the procedure is very effective in recognizing simila r objects. (C) 1998 Elsevier Science Ltd. All rights reserved.