Abstract
Off-line handwritten Chinese character recognition (Off-HCCR) is one of the most challenging topics in pattern recognition. This paper first presents to use Gabor filters and Zernike moments to extract local and global features of handwritten Chinese characters. Then, fusion features are classified by naïve Bayesian network, which performs surprisingly well when inputted features are conditionally independent. A recognition system based on these approaches is built, and experiments are performed on 50 categories frequently used handwritten Chinese characters. Results indicate that the proposed methods are effective.
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
Shi D. (2003) “Offline handwritten Chinese character recognition by radical decomposition”, ACM Transactions on Asian Language Information Processing, vol.2, no.1, pp:27–48.
Shustorovich A. (1994) “A subspace projection approach to feature extraction: the two-dimensional Gabor transform for character recognition”, Neural Networks, vol.7, no.8, pp:1295–1301.
Okajima K. (1997) “The Gabor function extracts the maximum information from input local signals”, Neural Networks, vol.11, pp:435–439.
Hamamoto Y., et al. (1998) “A gabor filter-based method for recognizing handwritten numerals”, Pattern Recognition, vol.31, no.4, pp:395–400.
The C. H., Chin R. T. (1988) “On image analysis by the method of moments”, IEEE Trans. Pattern Anal. Machine Intell., vol.10, no.4, pp:496–513.
Belkasim S. O. (1991) “Pattern recognition with moment invariants-a comparative study and new results”, Pattern Recognition, vol.24, no.12, pp:1117–1138.
Chong Chee-Way, Raveendran P., Mukundan R. (2003) “Translation invariants of Zernike moments”, Pattern Recognition, vol.36, pp:1765–1773.
Jensen F. (2001) Bayesian Networks and Decision Graphs, Springer-Verlag, New York.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gao, Y., Uozumi, T., Chen, F. (2005). Off-line handwritten Chinese character recognition based on fusion features and Bayesian classifier. In: Abraham, A., Dote, Y., Furuhashi, T., Köppen, M., Ohuchi, A., Ohsawa, Y. (eds) Soft Computing as Transdisciplinary Science and Technology. Advances in Soft Computing, vol 29. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-32391-0_62
Download citation
DOI: https://doi.org/10.1007/3-540-32391-0_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25055-5
Online ISBN: 978-3-540-32391-4
eBook Packages: EngineeringEngineering (R0)