This Article 
 Bibliographic References 
 Add to: 
Character Recognition Based on Attribute-Dependent Programmed Grammar
November 1992 (vol. 14 no. 11)
pp. 1122-1128

The recognition of Korean characters by a syntactic method is considered. Korean characters are composed of phonetic symbols in two dimensions and contain very little redundancy. In addition, the phonetic symbols in each character are different in shape and number depending on how they are composed. Thus, attribute information is important. A Korean character recognition algorithm based on an attribute-dependent programmed grammar is presented. The preprocessing and primitive extraction algorithm is also described. The algorithm was implemented and tested with more than 9600 Korean characters in pages randomly selected from children's story books. The algorithm based on the attribute-dependent programmed grammar recognized characters reasonably quickly, with more than 95.1% accuracy.

[1] J. D. Becker, "Typing Chinese, Japanese, and Korean,"IEEE Comput. Mag., vol. 18, no. 1, pp. 27-36, 1985.
[2] R. G. Casey and G. Nagy, "Decision tree design using a probabilistic model,"IEEE Trans. Inform. Theory, vol. IT-30, pp. 93-99, 1984.
[3] N. Chomsky, "Three models for the description of language,"IRE Trans. Inform. Theory, vol. IT-2, pp. 113-124, 1956.
[4] M. A. Eshera and K. S. Fu, "An image understanding system using attributed symbolic representation and inexact graph matching,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, no. 5, pp. 604-618, Sept. 1986.
[5] K. S. Fu,Syntactic Pattern Recognition and Applications. Englewood Cliffs, NJ: Prentice Hall, 1982.
[6] K. S. Fu, "A step toward unification of syntactic and statistical pattern recognition,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-5, no. 2, pp. 200-205, Mar. 1983.
[7] C. Guo and G. Xuan, "Automatic recognition of printed Chinese characters by four comer codes," inProc. 1986 Int. Conf. Patt. Recogn., pp. 1013-1015.
[8] S. Kahan, T. Pavlidis, and H. S. Baird, "On the recognition of printed characters of any font and size,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, pp. 274-288, 1987.
[9] Y. Kurosawa and H. Asada, "Attributed string matching with statistical constraints for character recognition," inProc. 1986 Int. Conf. Patt. Recogn., pp. 1063-1067.
[10] K. H. Lee, "A syntactic character recognition using attribute dependent grammar," Ph.D. dissertation, Inha Univ., Inchon, Korea, 1981.
[11] K. H. Lee, K. B. Eom, and R. L. Kashyap, "Character recognition using attributed grammar," inProc. 1988 IEEE Conf. Comput. Vision Patt. Recogn., (Ann Arbor, MI), 1988.
[12] J. Mantas, "An overview of character recognition methodologies,"Patt. Recogn., vol. 19, no. 6, pp. 425-430, 1986.
[13] S. Mori, K. Yamamoto, and M. Yasuda, "Research on machine recognition of handprinted characters,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, pp. 386-405, 1984.
[14] H. Nagahashi and M. Nakatsuyama, "A pattern description and generation method of structural characters,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, pp. 112-118, 1986.
[15] G. Nagy, "Optical character recognition--Theory and practice,"Handbook of Statistics(P. R. Krishnaish and L. N. Kanal, Eds.). 1982, vol. 2.
[16] A. Rosenfeld, "A characterization of parallel thinning algorithms,"Inform. Contr., vol. 29, pp. 286-291, 1975.
[17] A. Rosenfeld and E. Johnston, "Angle detection on digital curves,"IEEE Trans. Comput., vol. C-22, pp. 875-878, Sept. 1973.
[18] A. Rosenfeld and A. Kak,Digital Picture Processing, New York: Academic, 1976.
[19] D. J. Rosenkrantz, "Programmed grammar--A new device for generating formal languages," Ph.D. dissertation, Columbia Univ., New York, 1967.
[20] M. Shridhar and A. Badreldin, "High accuracy character recognition algorithm using fourier and topological descriptors,"Patt. Recogn., vol. 17, no. 5, pp. 515-524, 1984.
[21] S. Stefanelli and A. Rosenfeld, "Some parallel thinning algorithms for digital pictures,"J. ACM, vol. 18, pp. 255-264, 1971.
[22] F. W. M. Stentiford, "Automatic feature design for optical character recognition using an evolutionary search procedure,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-7, pp. 349-355, 1985.
[23] P. H. Swain and K. S. Fu, "Stochastic programmed grammars for syntactic pattern recognition,"Patt. Recogn., vol. 4, pp. 83-100, 1972.
[24] C. -H. Teh and R. T. Chin, "On the detection of dominant points on digital curves,"IEEE Trans. Patt. Anal. Machine Intell., vol. 11, no. 8, pp. 859-872, 1989.
[25] W. H. Tsai and K. S. Fu, "Attributed grammar--A tool for combining syntactic and statistical approaches to pattern recognition,"IEEE Trans. Syst. Man Cybern., vol. SMC-10, no. 12, pp. 873-885, Dec. 1980.
[26] J. Tsukumo and K. Asai, "Machine printed Chinese and Japanese character recognition methods and experiments for reading Japanese pocket books," inProc. IEEE Conf. Comput. Vision Patt. Recogn., 1986, pp. 162-167.
[27] G. T. Toussaint, "The use of context in pattern recognition,"Patt. Recogn.vol. 10, pp. 189-204, 1978.
[28] K. C. You and K. S. Fu, "A syntactic approach to shape recognition using attributed grammars,"IEEE Trans. Syst. Man Cybern., vol. SMC-9, no. 6, pp. 134-345, 1979.

Index Terms:
attribute-dependent programmed grammar; phonetic symbols; Korean character recognition; primitive extraction; attribute grammars; character recognition
K.H. Lee, K.B. Eom, R.L. Kashyap, "Character Recognition Based on Attribute-Dependent Programmed Grammar," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 11, pp. 1122-1128, Nov. 1992, doi:10.1109/34.166629
Usage of this product signifies your acceptance of the Terms of Use.