This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance
March 1999 (vol. 21 no. 3)
pp. 258-262

Abstract—This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DEF) from each character image, transformation based on partial inclination detection (TPID) is used to reduce undesired effects of degraded images. In the recognition process, city block distance with deviation (CBDD) and asymmetric Mahalanobis distance (AMD) are proposed for rough classification and fine classification. With this recognition system, the experimental result of the database ETL9B reaches to 99.42%.

[1] R. Casey and G. Nagy, "Recognition of Printed Chinese Characters," IEEE Trans. Electronic Computers, vol. 15, no.1, pp. 91-101, 1966.
[2] F.H. Cheng, "Multi-Stroke Relaxation Matching Method for Handwritten Chinese Character Recognition," Pattern Recognition, vol. 31, no. 4, pp. 401-410, 1998.
[3] H.W. Hao, X.H. Xiao, and R.W. Dai, "Handwritten Chinese Character Recognition by Metasynthetic Approach," Pattern Recognition, vol. 30, no. 8, pp. 1,321-1,328, 1997.
[4] T.W. Hildebrandt and W. Liu, "Optical Recognition of Handwritten Chinese Characters: Advances Since 1980," Pattern Recognition, vol. 26, no. 2, pp. 205-225, 1993.
[5] J. Tsukumo, "Improved Algorithm for Direction Pattern Matching and Its Application for Handprinted Kanji Character Classification," IEICE Technical Report, PRU90-20, 1990.
[6] H. Kato, S. Yokozuka, and H. Kida, "Recognition of Handwritten Character Using Peripheral Bend Contributivity," IEICE Technical Report, PRU95-3, 1995.
[7] Y. Shimada, M. Ohkura, M. Shiono, and R. Hashimoto, "On Discrimination of Handwritten Similar Kanji Characters by Multiple Feature Subspace Method," Trans. IEICE, vol. J78-D-11, no. 10, pp. 1,460-1,468, Oct. 1995.
[8] K. Saruta, N. Kato, M. Abe, and Y. Nemoto, "High Accuracy Recognition of ETL9B Using Exclusive Learning Neural Network—II (ELNET-II)," Trans. IEICE, vol. E79-D, no. 5, pp. 516-522, May 1996.
[9] F. Sun, S. Omachi, and H. Aso, "Precise Selection of Candidates for Handwritten Character Recognition Using Feature Regions," Trans. IEICE, vol. E79-D, no. 5, pp. 510-515, May 1996.
[10] T. Wakabayashi, Y. Deng, S. Tsuruoka, F. Kimura, and Y. Miyake, "Accuracy Improvement by Nonlinear Normalization and Feature Compression in Handwritten Chinese Character Recognition," Trans. IEICE, vol. J79-D-II, no. 5, pp. 765-774, May 1996.
[11] N. Kato, M. Abe, and Y. Nemoto, "A Handwritten Character Recognition System Using Modified Mahalanobis Distance," Trans. IEICE, vol. J79-D-II, no. 1, pp. 45-52, Jan. 1996.
[12] N. Sun, M. Abe, and Y. Nemoto, "A Handwritten Character Recognition System by Using Improved Directional Element Feature and Subspace Method," Trans. IEICE, vol. J78-D-II, no. 6, pp. 922-930, June 1995.
[13] M. Suzuki, N. Kato, H. Aso, and Y. Nemoto, "A Handprinted Character Recognition System Using Image Transformation Based on Partial Inclination Detection," Trans. IEICE, vol. E79-D, no. 5, pp. 504-509, May 1996.
[14] T. Saito, H. Yamada, and K. Yamamoto, "On the Data Base ETL9 of Handprinted Characters in JIS Chinese Characters and Its Analysis," Trans. IEICE, vol. J68-D, no. 4, pp. 757-764, Apr. 1985.
[15] H. Yamada, T. Saito, and K. Yamamoto, "Line Density Equalization—A Nonlinear Normalization for Correlation Method," Trans. IEICE, vol. J67-D, no. 11, pp. 1,379-1,383, Nov. 1984.
[16] M. Shiono, T. Koyama, H. Sanada, and Y. Tezuka, "Recognition of Handprinted Characters by Simplified Elastic Matching Method," Trans. IEICE, vol. J64-D, no. 5, pp. 387-394, May 1981.
[17] J. Guo, N. Sun, Y. Nemoto, M. Kimura, H. Echigo, and R. Sato, "Recognition of Handwritten Characters Using Pattern Transformation Method With Cosine Function," Trans. IEICE, vol. J76-D-II, no. 4, pp. 835-842, Apr. 1993.
[18] M. Yasuda, K. Yamamoto, and H. Yamada, "Effect of the Perturbed Correlation Method for Optical Character Recognition," Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 830-833, 1993.
[19] T. Ejima, Y. Nakamura, and M. Kimura, "The Characteristic Feature Based on Four Types of Structural Information and Their Effectiveness for Character Recognition," Trans. IEICE, vol. J68-D, no. 4, pp.789-796, 1985.
[20] S.J. Raudys and A.K. Jain, "Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 252-264, 1991.
[21] T. Takeshita, F. Kimura, and Y. Miyake, "On the Estimation Error of Mahalanobis Distance," Trans. IEICE, vol. J70-D, no. 3, pp. 567-573, Mar. 1987.

Index Terms:
Handwritten Chinese and Japanese character recognition, directional element feature, city block distance with deviation, asymmetric Mahalanobis distance, ETL9B.
Citation:
Nei Kato, Masato Suzuki, Shin'ichiro Omachi, Hirotomo Aso, Yoshiaki Nemoto, "A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 3, pp. 258-262, March 1999, doi:10.1109/34.754617
Usage of this product signifies your acceptance of the Terms of Use.