×

Recognition of handwritten Chinese characters by critical region analysis. (English) Zbl 1187.68469

Summary: The problem of recognizing offline handwritten Chinese characters has been investigated extensively. One difficulty is due to the existence of characters with very similar shapes. In this paper, we propose a “critical region analysis” technique which highlights the critical regions that distinguish one character from another similar character. The critical regions are identified automatically based on the output of the Fisher’s discriminant. Additional features are extracted from these regions and contribute to the recognition process. By incorporating this technique into the character recognition system, a record high recognition rate of 99.53% on the ETL-9B database is obtained.

MSC:

68T10 Pattern recognition, speech recognition
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] J. Tsukumo, H. Tanaka, Classification of handprinted Chinese characters using non-linear normalization and correlation methods, in: Proceedings of the Ninth International Conference on Pattern Recognition, Roma, Italy, 1988, pp. 168-171.; J. Tsukumo, H. Tanaka, Classification of handprinted Chinese characters using non-linear normalization and correlation methods, in: Proceedings of the Ninth International Conference on Pattern Recognition, Roma, Italy, 1988, pp. 168-171.
[2] Yamada, H.; Yamamoto, K.; Saito, T., A nonlinear normalization method for handprinted kanji character recognition-line density equalization, Pattern Recognition, 23, 9, 1023-1029 (1990)
[3] T. Horiuchi, R. Haruki, H. Yamada, K. Yamamoto, Two dimensional extension of nonlinear normalization method using line density for character recognition, in: Proceedings of the Fourth International Conference on Document Analysis and Recognition, Ulm, Germany, 1997, pp. 511-514.; T. Horiuchi, R. Haruki, H. Yamada, K. Yamamoto, Two dimensional extension of nonlinear normalization method using line density for character recognition, in: Proceedings of the Fourth International Conference on Document Analysis and Recognition, Ulm, Germany, 1997, pp. 511-514.
[4] C.-L. Liu, H. Sako, H. Fujisawa, Handwritten Chinese character recognition: alternatives to nonlinear normalization, in: Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, Scotland, 2003, pp. 524-528.; C.-L. Liu, H. Sako, H. Fujisawa, Handwritten Chinese character recognition: alternatives to nonlinear normalization, in: Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, Scotland, 2003, pp. 524-528.
[5] Liu, C.-L.; Marukawa, K., Pseudo two dimensional shape normalization methods for handwritten Chinese character recognition, Pattern Recognition, 38, 12, 2242-2255 (2005)
[6] Kimura, F.; Takashina, K.; Tsuruoka, S.; Miyake, Y., Modified quadratic discriminant functions and the application to Chinese character recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 9, 1, 149-153 (1987)
[7] Liu, C.-L.; Sako, H.; Fujisawa, H., Performance evaluation of pattern classifiers for handwritten character recognition, International Journal on Document Analysis Recognition, 4, 191-204 (2002)
[8] C.-L. Liu, High accuracy handwritten Chinese character recognition using quadratic classifiers with discriminative feature extraction, in: Proceedings of the 18th International Conference on Pattern Recognition, vol. 2, Hong Kong, 2006, pp. 942-945.; C.-L. Liu, High accuracy handwritten Chinese character recognition using quadratic classifiers with discriminative feature extraction, in: Proceedings of the 18th International Conference on Pattern Recognition, vol. 2, Hong Kong, 2006, pp. 942-945.
[9] Kato, N.; Suzuki, M.; Omachi, S.; Aso, H.; Nemoto, Y., A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance, IEEE Transactions on Pattern Analysis and Machine Intelligence, 21, 3, 258-262 (1999)
[10] Dong, J.-X.; Krzyzak, A.; Suen, C.-Y., Fast SVM training algorithm with decomposition on very large training sets, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 4, 603-618 (2005)
[11] Dong, J.-X.; Krzyzak, A.; Suen, C.-Y., An improved handwritten Chinese character recognition system using support vector machine, Pattern Recognition Letters, 26, 1849-1856 (2005)
[12] Sun, Q.; Wang, L.-L.; Lim, S.-H.; DeJong, G., Robustness through prior knowledge: using explanation-based learning to distinguish handwritten Chinese characters, International Journal on Document Analysis and Recognition, 10, 175-186 (2007)
[13] Fu, H.-C.; Xu, Y.-Y., Multilinguistic handwritten character recognition by Bayesian decision-based neural networks, IEEE Transactions on Signal Processing, 46, 10, 2781-2789 (1998)
[14] Mao, J.; Mohiuddin, K. M., Improving OCR performance using character degradation models and boosting algorithm, Pattern Recognition Letters, 18, 1415-1419 (1997)
[15] G. Chen, H.-G. Zhang, J. Gao, Learning pattern generation for handwritten Chinese character using pattern transform method with cosine function, in: Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian, 2006, pp. 3329-3333.; G. Chen, H.-G. Zhang, J. Gao, Learning pattern generation for handwritten Chinese character using pattern transform method with cosine function, in: Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian, 2006, pp. 3329-3333.
[16] H. Miyao, M. Maruyama, Virtual example synthesis based on PCA for off-line handwritten character recognition, in: Proceedings of the Seventh International Workshop on Document Analysis Systems, Nelson, New Zealand, 2006, pp. 96-105.; H. Miyao, M. Maruyama, Virtual example synthesis based on PCA for off-line handwritten character recognition, in: Proceedings of the Seventh International Workshop on Document Analysis Systems, Nelson, New Zealand, 2006, pp. 96-105.
[17] Kimura, F.; Wakabayashi, T.; Tsuruoka, S.; Miyake, Y., Improvement of handwritten Japanese character recognition using weighted direction code histogram, Pattern Recognition, 30, 8, 1329-1337 (1997)
[18] C.-H. Leung, Y.-S. Cheung, K.-P. Chan, A distortion model for Chinese character generation, in: Proceedings of the 1985 IEEE International Conference on Systems, Man and Cybernetics, Tucson, Arizona, 1985, pp. 38-41.; C.-H. Leung, Y.-S. Cheung, K.-P. Chan, A distortion model for Chinese character generation, in: Proceedings of the 1985 IEEE International Conference on Systems, Man and Cybernetics, Tucson, Arizona, 1985, pp. 38-41.
[19] K.-C. Leung, C.-H. Leung, Recognition of handwritten chinese characters by combining regularization, Fisher’s discriminant and distorted sample generation, in: Proceedings of the 10th International Conference on Document Analysis and Recognition, Barcelona, 2009, pp. 1026-1030.; K.-C. Leung, C.-H. Leung, Recognition of handwritten chinese characters by combining regularization, Fisher’s discriminant and distorted sample generation, in: Proceedings of the 10th International Conference on Document Analysis and Recognition, Barcelona, 2009, pp. 1026-1030.
[20] Gao, T.-F.; Liu, C.-L., High accuracy handwritten Chinese character recognition using LDA-based compound distances, Pattern Recognition, 41, 11, 3442-3451 (2008) · Zbl 1167.68436
[21] M. Hamanaka, K. Yamada, J. Tsukumo, Normalization-cooperated feature extraction method for handprinted kanji character recognition, in: Proceedings of the Third International Workshop on Frontiers of Handwriting Recognition, Buffalo, New York, 1993, pp. 343-348.; M. Hamanaka, K. Yamada, J. Tsukumo, Normalization-cooperated feature extraction method for handprinted kanji character recognition, in: Proceedings of the Third International Workshop on Frontiers of Handwriting Recognition, Buffalo, New York, 1993, pp. 343-348.
[22] Duda, R. O.; Hart, P. E.; Stork, D. G., Pattern Classification (2001), Wiley: Wiley New York · Zbl 0968.68140
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.