Recognizing handwritten Chinese day and month words by combining a holistic method and a segmentation-based method

摘要

Chinese words and phrases often appear in various types of form tables, and many of them have a small vocabulary. To segment and recognize Chinese words and phrases is a challenging task because they contain an uncertain number of characters and might be cursively written, and segmentation might produce crack or noise characters. In this paper, we propose to combine a holistic method and a segmentation-based method for recognizing the Chinese day and month item on Chinese checks. The holistic method takes all the characters as a single unit and recognizes the unit without segmentation. The segmentation-based method segments a word into the predicted number of characters and then recognizes them. First, it uses projection and structure analysis to find as many candidate segmentation lines as possible. Then, it exploits a predicted word length to reduce the segmentation lines. Finally, it uses recognition scores to select the optimal recognition result. The encouraging experimental results show that our method is feasible and powerful.