Skip to main content
Log in

A new linguistic decoding method for online handwritten Chinese character recognition

  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This paper presents a new linguistic decoding method for online handwritten Chinese character recognition. The method employs a hybrid language model which combinesN-gram and linguistic rules by rule quantification technique. The linguistic decoding algorithm consists of three stages: word lattice construction, the optimal sentence hypothesis search and self-adaptive learning mechanism. The technique has been applied to palmtop computer’s online handwritten Chinese character recognition. Samples containing millions of characters were used to test the linguistic decoder. In the open experiment, accuracy rate up to 92% is achieved, and the error rate is reduced by 68%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Wang Xuan. The research of computational language model of speech and character input [dissertation]. Harbin Institute of Technology, 1997, pp.60–70.

  2. McMahon J, Smith F J. A review of statistical language processing technology.Artificial Intelligence Review, the Queen’s University of Belfast, Ireland, 1998, 12(5): 347–391.

    Article  Google Scholar 

  3. Ronald Rosenfeld. Adaptive statistical language modeling: A maximum entropy approach [dissertation]. Carhegie Mellon University, Pittsburgh, PA, April 1994, pp. 1–8.

    Google Scholar 

  4. Andrew R Golding. A Bayestan hybrid method for context-sensitive spelling correction. InProceedings of the Third Workshop on Very Large Corpora, Cambridge, MA, 1995, pp.39–53.

  5. Joerg Ueberla. Analyzing and improving statistical language models for speech recognition [dissertation]. School of Computer Science of Simon Fraser University, Vancouver, British Columbia, Canada, May 1994, pp.15–25.

    Google Scholar 

  6. Andrew R Golding Yues Schabes. Combining trigram-based and feature-based methods for contextsensitive spelling correction. InProceedings of the 34th Annual meeting of the Association for Computational Lingustitics, Santa Cruz, CA, 1996, pp.71–78.

  7. G Jan Wilms. Using a hybrid system of corpus and knowledge-based techniques to automate the induction of a lexical sublanguage grammar. Inthe 16th International Conference on Computational Linguistics, Copenhagen, Denmark, 1996, 4: 1163–1167.

  8. Stanley F Chen. Building probabilistic models for natural language [dissertation]. School of Computer Science of Harvard University, Cambridge, Massachusetts, May 1996 pp. 5–15.

    Google Scholar 

  9. Mosur K Ravishankar. Efficient algorithm for speech recognition [dissertation]. Carnegie Mellon University, Pittsburgh, PA, 1996, pp. 4–9.

    Google Scholar 

  10. Brigitte Krenn, Christer Samuelsson. The linguist’s guide to statistics. A compendium for a course in Statistical Approaches in Computational Linguistics held at the University of the Saarland, 1994, pp.41–48.

  11. Wang Xiaolong. The problem of the fewest segmentation and its solution.Chinese Science Bulletin, 1989, 33(11): 30–35.

    Google Scholar 

  12. Tang Xianglong, Shu Wenhao, Liu Jiafenget al. The system of online handwritten Chinese character recognition based Association.Information and Control, 1991, 20(5): 18–21.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Xu Zhiming.

Additional information

This research was supported by the National ‘863’ High-Tech programme of China (No.863-306-03-02-1).

XU Zhiming was born in 1967. He is a Ph.D. candidate in Computer Science Department of Harbin Institute of Technology. His research interests include handwritten Chinese character recognition, natural language processing.

WANG Xiaolong was born in 1955. He is a professor and a Ph.D. supervisor in Computer Science Department of Harbin Institute of Technology. His research interests include artificial intelligence, natural language processing.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Xu, Z., Wang, X. A new linguistic decoding method for online handwritten Chinese character recognition. J. Comput. Sci. & Technol. 15, 597–603 (2000). https://doi.org/10.1007/BF02948842

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02948842

Keywords

Navigation