Abstract
Given the large number of categories, or class types, in the Chinese language, the challenge offered by character recognition involves dealing with such a large-scale problem in both training and testing phases. This paper addresses three techniques, the combination of which has been found to be effective in solving the problem. The techniques are: 1) a prototype learning/matching method that determines the number and location of prototypes in the learning phase, and chooses the candidates for each character in the testing phase; 2) support vector machines (SVM) that post-process the top-ranked candidates obtained during the prototype learning or matching process; and 3) fast feature-vector matching techniques to accelerate prototype matching via decision trees and sub-vector matching. The techniques are applied to Chinese handwritten characters, expressed as feature vectors derived by extraction operations, such as nonlinear normalization, directional feature extraction, and feature blurring.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cortes, C., Vapnik, V.: Support-vector network. In: Machine Learning, vol. 20, pp. 273–297 (1995)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Bottou, L., Cortes, C., Denker, J., Drucker, H., Guyon, I., Jackel, L., LeCun, L., Muller, U., Sackinger, E., Simard, P., Vapnik, V.: Comparison of classifier methods: A case study in handwriting digit recognition. In: Proc. Int. Conf. Pattern Recognition., pp. 77–87 (1994)
Knerr, S., Personnaz, L., Dreyfus, G.: Single-layer learning revisited: A stepwise procedure for building and training a neural network. In: Fogelman, J. (ed.) Neurocomputing: Algorithms, Architectures and Applications, Springer, New York (1990)
Platt, Cristianini, N., Shawe-Taylor, J.: Large margin DAG’s for multiclass classification. Advances in Neural Information Processing Systems 12, 547–553 (2000)
Chang, F., Lin, C.-C., Chen, C.J.: Applying a Hybrid Method to Handwritten Char-acter Recognition. In: Intern. Conf. Pattern Recognition 2004, Cambridge, vol. 2, pp. 529–532 (2004)
Chou, C.H., Lin, C.C., Liu., Y.H., Chang, F.: A Prototype Classification Method and Its Use in A Hybrid Solution for Multiclass Pattern Recognition. Pattern Recogni-tion 39(4), 624–634 (2006)
Liu, Y.-H., Lin, C.-C., Lin, W.-H., Chang, F.: Accelerating Feature-Vector Matching Using Multiple-Tree and Sub-Vector Methods. Pattern Recognition 40(9), 2392–2399 (2007)
Chang, F., Lin, C.-C., Lu, C.-J.: Adaptive Prototype Learning Algorithms: Theo-retical and Experimental Studies. Journal of Machine Learning Research 7, 2125–2148 (2006)
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Chapman and Hall, New York (1984)
Quinlan, J.R.: Induction of Decision Tree. Machine Learning 1(1), 81–106 (1986)
Chang, F., Lin, C.-C., Chen, C.-J.: A hybrid method for multiclass classification and its application to handwritten character recognition. Institute of Information Science, Academia Sinica, Taipei, Taiwan, Tech. Rep. TR-IIS-04-016 (2004)
Chang, F., Chou, C.-H., Lin, C.-C., Chen, C.-J.: A prototype classification method and its application to handwritten character recognition. In: IEEE SMC, Hague (2004)
Chang, F., Lin, C.-C., Chen, C.-J.: Applying a hybrid method to handwritten character recognition. In: Proc.17th Intern. Conf. Pattern Recognition, pp. 529–532 (2004)
Lee, S.-W., Park, J.-S.: Nonlinear shape normalization methods for the recognition of large-set handwritten characters. Pattern Recognition 27(7), 895–902 (1994)
Yamada, H., Yamamoto, K., Saito, T.: A nonlinear normalization method for hand-printed Kanji character recognition – line density equalization. Pattern Recognition 23(9), 1023–1029 (1990)
Liu, C.-L., Kim, I.-J., Kim, J.H.: High accuracy handwritten Chinese character recognition by improved feature matching method. In: Proc. 4th Intern. Conf. Document Analysis and Recognition, pp. 1033–1037 (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chang, F. (2008). Techniques for Solving the Large-Scale Classification Problem in Chinese Handwriting Recognition. In: Doermann, D., Jaeger, S. (eds) Arabic and Chinese Handwriting Recognition. SACH 2006. Lecture Notes in Computer Science, vol 4768. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78199-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-78199-8_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78198-1
Online ISBN: 978-3-540-78199-8
eBook Packages: Computer ScienceComputer Science (R0)