On-line handwritten Chinese character recognition directed by components with dynamic templates

摘要

Structural matching has been recognized as a promising approach for on-line Chinese character recognition. In order to reduce its great computational complexity and improve its performance, people have been seeking for ways to direct the matchingof a whole character by the result of partial matching. In this paper, the authors proposed 45 basic components for 3,755 categories of daily-used Chinese characters to direct the stroke segment matching of whole characters. Since they are always locatedat either the beginning or the end of the stroke segment string of characters, these components are easy to be extracted and separated from other parts of a character. Besides, in our approach, the reference templates of these components are extracteddynamically from the corresponding segment string of characters when a specific matching is carried out. This strategy avoids building multiple templates for the components of the same kind hut at different places of characters. The experiments show thatthe segment matching computation has been reduced greatly without reducing the correctness of matching.