A fuzzy rule-based system for handwritten Chinese characters recognition based on radical extraction

Abstract In this paper, a fuzzy rule-based system for handwritten Chinese characters recognition (HCCR) based on radical extraction is proposed. Since the writings of handwritten Chinese characters vary a lot, we adopt fuzzy set theory to deal with the recognition of these fuzzy patterns. Candidates of strokes are provided with confidence values to obtain more reliable and accurate results. Furthermore, hierarchical fuzzy rule sets that represent the character structures are used to combine the extracted strokes into compound strokes or radicals. The flexible expansion ability thus provided is very promising. Also, since the number of rules in a fuzzy system is much less than that in a general rule-based system, the computation effort is not difficult. An average of 99.63% recognition rate of 542 test categories that are selected from the 100th sample set of HCCRBASE (character image database provided by CCL, ITRI, Taiwan) is obtained. The experimental results not only verify the feasibility of the proposed system, but also suggest that applying fuzzy set theory to HCCR is an efficient and promising approach.

[1]  Fang-Hsuan Cheng,et al.  Research on Chinese OCR in Taiwan , 1991, Int. J. Pattern Recognit. Artif. Intell..

[2]  Fang-Hsuan Cheng,et al.  Fuzzy approach to solve the recognition problem of handwritten chinese characters , 1989, Pattern Recognit..

[3]  Hahn-Ming Lee,et al.  Fuzzy feature extraction on handwritten Chinese characters , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[4]  A. Kandel,et al.  Applicability of some fuzzy implication operators , 1989 .

[5]  Constantin V. Negoita,et al.  On Fuzzy Systems , 1978 .

[6]  Hsi-Jian Lee,et al.  A Probabilistic Stroke-Based Viterbi Algorithm for Handwritten Chinese Characters Recognition , 1993, Int. J. Pattern Recognit. Artif. Intell..

[7]  Fang-Hsuan Cheng,et al.  Recognition of handprinted chinese characters via stroke relaxation , 1993, Pattern Recognit..

[8]  Hideo Ogawa,et al.  Thinning and stroke segmentation for handwritten Chinese character recognition , 1982, Pattern Recognit..

[9]  J. Keller,et al.  Fuzzy set theoretic approach to computer vision: An overview , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[10]  Wentai Liu,et al.  Optical recognition of handwritten Chinese characters: Advances since 1980 , 1993, Pattern Recognit..

[11]  Jhing-Fa Wang,et al.  Preclassification for handwritten chinese character recognition by a peripheral shape coding method , 1993, Pattern Recognit..

[12]  Yung-Sheng Chen,et al.  A modified fast parallel algorithm for thinning digital patterns , 1988, Pattern Recognit. Lett..

[13]  Jun Gu,et al.  A Constrained Approach to Multifont Chinese Character Recognition , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  William Stallings,et al.  Approaches to chinese character recognition , 1976, Pattern Recognit..

[15]  James B. Kuo,et al.  A coded block adaptive neural network system with a radical-partitioned structure for large-volume Chinese characters recognition , 1992, Neural Networks.

[16]  Hsi-Jian Lee,et al.  Off-line recognition of handwritten Chinese characters by on-line model-guided matching , 1992, Pattern Recognit..

[17]  Sankar K. Pal,et al.  Image description and primitive extraction using fuzzy sets , 1983, IEEE Transactions on Systems, Man, and Cybernetics.