Two-layer assignment method for online Chinese character recognition

A method of stroke order and number-free online recognition of Chinese char acters is proposed. Both input characters and model characters are represen ted with complete relational graphs (CRGs). Classification of an input char acter can be implemented by matching its CRG against every CRG of the model base. However, efficient algorithms for graph matching are not available. Therefore, the graph-matching problem is transformed into a two-layer assig nment problem and is solved with the Hungarian method. Two complexity reduc tion schemes are presented to save computational time. Tests demonstrate th e efficiency of the proposed method.