This Article 
 Bibliographic References 
 Add to: 
Statistical Character Structure Modeling and Its Application to Handwritten Chinese Character Recognition
November 2003 (vol. 25 no. 11)
pp. 1422-1436

Abstract—This paper proposes a statistical character structure modeling method. It represents each stroke by the distribution of the feature points. The character structure is represented by the joint distribution of the component strokes. In the proposed model, the stroke relationship is effectively reflected by the statistical dependency. It can represent all kinds of stroke relationship effectively in a systematic way. Based on the character representation, a stroke neighbor selection method is also proposed. It measures the importance of a stroke relationship by the mutual information among the strokes. With such a measure, the important neighbor relationships are selected by the nth order probability approximation method. The neighbor selection algorithm reduces the complexity significantly because we can reflect only some important relationships instead of all existing relationships. The proposed character modeling method was applied to a handwritten Chinese character recognition system. Applying a model-driven stroke extraction algorithm that cooperates with a selective matching algorithm, the proposed system is better than conventional structural recognition systems in analyzing degraded images.The effectiveness of the proposed methods was visualized by the experiments. The proposed method successfully detected and reflected the stroke relationships that seemed intuitively important. The overall recognition rate was 98.45 percent, which confirms the effectiveness of the proposed methods.

[1] H.Y. Kim and J.H. Kim, Hierarchical Random Graph Representation of Handwritten Characters and Its Application to Hangul Recognition Pattern Recognition, vol. 34, no. 2, pp. 187-201, 2001.
[2] H.Y. Kim and Y.S. Nam, Handwritten Hangul Word Recognition Based on Character Segmentation Proc. Fourth Character Recognition Workshop, pp. 123-131, 2000.
[3] F.H. Cheng, Multi-Stroke Relaxation Matching Method for Handwritten Chinese Character Recognition Pattern Recognition, vol. 31, no. 4, pp. 401-410, 1998.
[4] H.J. Lee and B. Chen, Recognition of Handwritten Chinese Characters via Short Line Segments Pattern Recognition, vol. 25, no. 5, pp. 543-552, 1992.
[5] C.L. Liu, I.J. Kim, and J.H. Kim, Model-Based Stroke Extraction and Matching by Heuristic Search for Handwritten Chinese Character Recognition Proc. Sixth Int'l Workshop Frontiers in Handwriting Recognition, pp. 547-556, 1998.
[6] X. Zhang and Y. Xia, The Automatic Recognition of Handprinted Chinese Characters A Method of Extracting an Order Sequence of Strokes Pattern Recognition Letters, vol. 1, no. 4, pp. 259-265, 1983.
[7] L.H. Chen and J.R. Lieh, Handwritten Character Recognition Using a 2-Layer Random Graph by Relaxation Matching Pattern Recognition, vol. 23, no. 11, pp. 1189-1205, 1990.
[8] K.Y. Chris and F. Chung, Development of a Structural Deformable Model for Handwritten Recognition Proc. 11th Int'l Cconf. Pattern Recognition, pp. 1130-1133, 1998.
[9] T. Nagasaki, T. Yanagida, and M. Nakagawa, Relaxation-Based Pattern Matching Using Automatic Differentiation for Off-Line Character Recognition Proc. Fifth Int'l Conf. Document Analysis and Recognition, pp. 229-232, 1999.
[10] D. Nychka, A South Boulder Guide to Spatial Statistics National Center for Atmospheric Research,http://www.cgd. , Mar. 2003.
[11] P.M. Lewis, Approximating Probability Distributions to Reduce Storage Requirement Information and Control, vol. 2, pp. 214-225, Sept. 1959.
[12] C.K. Chow and C.N. Liu,"Approximating discrete probability distributions with dependence trees," IEEE Trans. Information Theory, vol. 14, no. 3, pp. 462-467, May 1968.
[13] H.J. Kang, K. Kim, and J.H. Kim, A Framework for Probabilistic Combination of Multiple Classifiers at an Abstract Level Eng. Applications of Artificial Intelligence, vol. 10, no. 4, pp. 379-385, 1997.
[14] T.K. Moon, Information Theory Lecture Note, Utah Univ., 7680lecture9.pdf, Mar. 2003.
[15] D.-H. Han and S.-B. Cho, A Knowledge-Based Thinning Algorithm for Off-Line Handwritten Hangul J. Korea Information Science Soc. (B), vol. 25, no. 9, pp. 1381-1388, 1998.
[16] R.O. Duda and P.E. Hart, Pattern Classification and Scene Anaysis. pp. 337-339, New York: Wiley-Interscience, 1973.
[17] H. Yamada, K. Yamamoto, and T. Saito, “A Nonlinear Normalization Method for Handprinted Kanji Character Recognition—lLine Density Equalization,” Pattern Recognition, vol. 23, no. 9, pp. 1023-1029, 1990.
[18] C.L. Liu, I.J. Kim, and J.H. Kim, Model-Based Stroke extraction and Matching for Handwritten Chinese Character Recognition Pattern Recognition, vol. 34, no. 12, pp. 2339-2352, 2001.

Index Terms:
Character recognition, statistical character structure modeling, model-driven stroke extraction, selective matching, heuristic search.
In-Jung Kim, Jin-Hyung Kim, "Statistical Character Structure Modeling and Its Application to Handwritten Chinese Character Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 11, pp. 1422-1436, Nov. 2003, doi:10.1109/TPAMI.2003.1240117
Usage of this product signifies your acceptance of the Terms of Use.