Relaxation Matching for Chinese Character Recognition Using Adjacency List

Due to the complexity in structure and the various distortions in different styles of Chinese characters, it is more suitable to use a structural matching algorithm for computer recognition of Chinese characters. Relaxation matching is a powerful technique which can tolerate considerable distortion. In this paper, we apply a new relaxation matching technique to character recognition based on constraint relation. The correlativity relation of strokes will be verified after the initialization matching. Several rules are devised for the relaxation matching. Adjacency list structure is use to storage the information of strokes. The structure makes matching more effective. The purpose is to achieve optimal matching.