In this paper a coarse classification scheme is proposed to speed up the recognition process of machine printed Chinese character. Simple and stable features are extracted by encoding feature points into a codeword of length 16. Geometrically, the codeword represents the distribution of feature points among character strokes. Using these simple features to do coarse classification can eliminate a large number of impossible candidates. Only few surviving candidates need be re-checked in the following more complex recognition algorithms. This scheme ill simplify the design of the classifier algorithm and reduce the recognition time. Some experimental results are given to show the validity and efficiency of our proposed methods.
為了持續優化網站功能與使用者體驗,本網站將Cookies分析技術用於網站營運、分析和個人化服務之目的。
若您繼續瀏覽本網站,即表示您同意本網站使用Cookies。