BIPARTITE WEIGHTED MATCHING FOR ONLINE HANDWRITTEN CHINESE CHARACTER-RECOGNITION

The matching of line segments between input and prototype characters can be formulated as bipartite weighted matching problem. Under the assumption that the distance of the two line segments and the unmatched penalty of any line segment are given, the matching goal is to find a matching such that the sum of the weights of matching edges and the penalties of unmatched vertices is minimum. In this paper, the Hungarian method is applied to solve the matching problem by a reduction algorithm. Moreover, a greedy algorithm based on the Hungarian method is proposed by restricting the above matching which satisfies the constraints of geometric relation. For each iteration in the greedy algorithm, a matched pair is deleted if the relation of their neighbors does not match and a new matching is then found by applying Hungarian method. Finally, we can find a stable matching that preserves the geometric relation. We have implemented this method to recognize on-line Chinese handwritten characters permitting both stroke-order variation and stroke-number variation and a 91% recognition rate is attained.