Combinatorial coarse classification method for OLCCR
This paper presents a new coarse classification method based on combination of two independent approaches for on-line Chinese character recognition (OLCCR). Through introducing a feedback control provided by the fine classifier, we are able to reach a good trade-off betweenprecision and speed. In the paper, we make some theoretical analysis on the form of combination, and compare it with competing methods. Both theoretical analysis and experimental results show that our method has the characteristics of high correct rate, good recognition speed, being easy to control and adaptable to various needs for practical application through parameter adjustment.
Unable to display preview. Download preview PDF.
- Y.S Wu, X.Q.Ding, Chinese character recognition—principle, method and implement, Advanced education publishing house, 1992 (In Chinese)Google Scholar
- C.C.Tappert, “The state of the art in on-line handwriting recognition”, IEEE Trans. Patt. Anal. Machine. Intell., Vol. 12, No. 8, pp.787–808, 1990Google Scholar
- F.Nouboud and R.Plamondon, “On-line recognition of handprinted characters: suvery and beta tests”, Pattern Recognition, Vol.23, No.9, pp. 1031–1044, 1990Google Scholar
- Y.Xia,S.P.Ma,Z.H.Yang,J.P.Gong and Y.Yang, “Method and system for on-line recognizing constraint free Chinese character”, The fifth Conference on Oriental Language, pp.85–89 (in Chinese)Google Scholar
- T-Z.Lin and K-C.Fan, “Coarse classification of on-line chinese characteers via structure feature-based method”, Pattern Recognition, Vol.27, No. 10, pp. 1365–1377, 1994Google Scholar
- Y-T.Tsay and W-H.Tsai, “Attribute string matching by split-and-merge for on-line chinese character recongnition”, IEEE Trans. Patt.,Anal. Mach. Intell., Vol. 15, No.2, pp.180–185, 1993Google Scholar