| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Recognition of Handwritten Chinese Characters by Modified Hough Transform Techniques
April 1989 (vol. 11 no. 4)
pp. 429-439
Chinese characters are mapped from the spatial domain into the parametric one for stroke extraction, and the dynamic programming matching (DP matching) algorithm is applied to recognize Chinese characters. This method overcomes not only the problem of noise sensitivity in the local feature approach, but also the problem of being time consuming in the global feature approach. Results are presented for two experiments conducted for a database called ETL8, which contains 881 Chinese characters and 160 variations for each one, to prove the usefulness of the MHT and DP matching methods. An actual recognition rate of 94.5% was obtained for 351 Chinese characters in the ETL8.
[1] 429N. Hagita and I. Masuda, "Recognition of handprinted Chinese characters by directions of strokes,"Trans. IECE Japan, vol. PRL 81- 13, pp. 95-102, 1981.[2] S. Naito, K. Komori, and E. Yodogawa, "Stroke density feature for handprinted Chinese character recognition,"Trans. IECE Japan, vol. J64-D, pp. 757-764, 1981.[3] R. I. Oka, "Handwritten Chinese-Japanese character recognition by using cellular feature," inProc. Int. Conf. Pattern Recognition, vol. 2, 1982, pp. 783-785.[4] W. H. Hsu and F. H. Cheng, "Recognition of handwritten Chinese characters by structure analysis of strokes,"J. Comput. Processing Chinese&Oriental Languages, vol. 2, pp. 101-112, Oct. 1985.[5] Y. H. Mao, "The realization of machine recognition of the handwritten Chinese characters," inProc. Int. Conf. Chinese Language Comput. Soc., 1982, pp. 432-442.[6] K. Nakata, Y. Nakano, and Y. Uchikura, "Recognition of Chinese characters," inProc. Conf. Machine Perception of Patterns of Pictures, Teddington, 1972, pp. 45-52.[7] Y. X. Gu, Q. R. Wang, and C. Y. Suen, "Application of multilayer decision tree in computer recognition of Chinese characters,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, pp. 83-89, 1983.[8] P. P. Wang and R. C. Shiau, "Machine recognition of printed Chinese characters via transformation algorithms,"Pattern Recognition, vol. 5, pp. 303-321, 1973.[9] K. Sakai, S. Hirai, T. Kawada, S. Amano, and K. Mori, "An optical Chinese character reader," inProc. 3rd Int. Joint Conf. Pattern Recognition, Nov. 1976, pp. 122-126.[10] Y. Kurosawa, K. Maeda, H. Asada, and K. Sakai, "Experiment on Chinese character recognition based on complex similarity," inProc. IECE Japan Annu. Conf., 1981, pp. 71-79.[11] S. Mori, K. Yamamoto, and M. Yasuda, "Research on machine recognition of handprinted characters,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, pp. 386-405, 1984.[12] M. Yasuda and H. Fujisawa, "An improvement of correlation method for character recognition,"J. IECE Japan, vol. J62-D, pp. 217-224, 1979.[13] T. Saito, H. Yamada, and K. Yamamoto, "An analysis of handprinted Chinese characters,"J. IECE Japan, vol. J65-D, pp. 550- 557, 1982.[14] A. Shio and K. Komori, "A stroke extraction method for handprinted Chinese character recognition,"Trans. IECE Japan, vol. IE80-14, pp. 83-90, 1980.[15] W. H. Hsu, K. Takahashi, and H. Fujita, "An expansion of pen movement stroke extraction method to multifont Chinese character recognition,"Trans. IECE Japan, vol. J65-D, pp. 1159-1166, 1982.[16] Y. T. Wang and W. H. Hsu, "Stroke extraction and matching methods for handwritten Chinese characters recognition," in1984 Int. Comput. Symp., Taiwan, 1984, pp. 441-446.[17] H. A. Glucksman, "Classification of mixed font alphabetics by characteristic loci," inDig. 1st Annu. IEEE Comput. Conf., 1976, pp. 137-141.[18] "Research on handprinted Chinese character recognition,"Nikkei Electron., vol. 12-7, pp. 148-167, 1981.[19] P. V. C. Hough, "Method and mean for recognizing complex patterns," U.S. Patent 3069654, 1966.[20] R.O. Duda and P.E. Hart, "Use of the Hough transformation to detect lines and curves in pictures,"Commun. Ass. Comput. Mach., vol. 15, no. 1, pp. 11-15, Jan. 1972.[21] S. D. Shapiro, "Use of the Hough transform for image data compression,"Pattern Recognition, vol. 12, pp. 333-337, 1980.[22] D. H. Ballard, "Generalizing the Hough transform to detect arbitrary shapes,"Pattern Recognition, vol. 13, pp. 111-122, 1981.[23] L. S. Davis, "Hierarchical generalized Hough transform,"Pattern Recognition, vol. 15, pp. 277-285, 1982.[24] M. Kushnir, K. Abe, and K. Matsumoto, "An application of the Hough transform to the recognition of printed Hebrew characters,"Pattern Recognition, vol. 16, pp. 183-191, 1983.[25] M. Kushnir, K. Abe, and K. Matsumoto, "Recognition of handprinted Hebrew characters using features selected in the Hough transform space,"Pattern Recognition, vol. 18, pp. 103-114, 1985.[26] Y. S. Cheung and C. H. Leung, "Chain-code transform for Chinese character recognition," inProc. 1985 IEEE Int. Conf. Syst., Man, Cybern., Tucson, AZ, Nov. 1985, pp. 42-45.[27] T. R. Hsing, "Robust adaptive thresholder for document scanning application,"SPIE, Real Time Signal Processing, vol. 341, pp. 94- 98, 1982.[28] Y. S. Chen and W. H. Hsu, "A new parallel thinning algorithm for binary image," inProc. Nat. Comput. Symp., Taiwan, 1985, pp. 295-299.
Index Terms:
handwritten Chinese characters recognition; Hough transform; spatial domain; stroke extraction; dynamic programming matching; noise sensitivity; database; ETL8; character recognition; dynamic programming; transforms
Citation:
F.H. Cheng, W.H. Hsu, M.Y. Chen, "Recognition of Handwritten Chinese Characters by Modified Hough Transform Techniques," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 429-439, Apr. 1989, doi:10.1109/34.19042
