Refinement to the Chamfer matching for a “center-on” fit

Matching is a central problem in image analysis and pattern recognition. In order to develop a matching algorithm that provides the optimal fit (i.e. “center-on” fit attempting to position the model points at equal spacing from the target image) between the model and distorted target images, a hierarchical modified Chamfer matching system with the simulated annealing is proposed in this paper. Since efficiency and accuracy are important issues in image matching, the proposed approach employs a hierarchical approach (i.e. multiresolution pyramid) to speed up the matching process and then the simulated annealing is applied to the modified Chamfer matching scheme to achieve the optimal solution. Encouraging results have been achieved by the proposed technique. This suggests a strong potential alternative to automatic target recognition system.