Fusion Recognition of Courtesy and Legal Amounts on Chinese Handwritten Bank Checks

In this paper, a novel fusion recognition algorithm of courtesy and legal amounts in handwritten Chinese bank checks is presented. Unlike the other fusion methods based on the independent recognition results of courtesy and legal amount, this proposed fusion algorithm begins with the segmentation of legal amount with the guide of recognition candidates of courtesy amount. And then we fuse the recognition candidates of courtesy and legal amounts. The system is validated with 1053 real bank checks. When the substitution is 0.43%, the recognition rate at the amount level can reach 66.10%