Using semantics in matching cursive Chinese handwritten annotations

  • Matthew Y. Ma
  • Patrick S. P. Wang
Handwritten Character Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)

Abstract

We propose a semantic matching network for the matching of cursive Chinese handwritten annotations. This architecture combines the semantics of Chinese language with the traditional elastic ink matching. Using semantics can make the matching algorithm more intelligent by pre-selecting the most likely candidates before elastic ink matching is applied thus speed up the whole matching process. The semantic matching network can also establish a link between Chinese handwritten annotations and typed text, which can be used to match between these two. Our experiments show that 75 – 85% recall can be achieved with a speed improvement of 85% over traditional elastic ink matching.

Keywords

Edit Distance Radical Extraction Radical Code Handwriting Recognition Semantic Match 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    D.P. Ausubel, J.D. Novak, and H. Hanesian. Educational Psychology: A cognitive view. New York: HRW Co., 2nd Ed., 1978.Google Scholar
  2. 2.
    F. Cheng and W. Hsu. Research on Chinese OCR in Taiwan. In Character and Handwriting Recognition. P.S.P. Wang (ed.), pages 139–164. World Scientific, 1991.Google Scholar
  3. 3.
    J. Liu, W.K. Cham, and M.M.Y. Chang. Stroke order and stroke number free on-line Chinese character recognition using attributed relational graph matching. In Proc. 13th ICPR, pages 259–263, August 1996.Google Scholar
  4. 4.
    D. Lopresti, M. Ma, P.S.P. Wang, and J. Crisman. Ink matching of cursive Chinese handwritten annotations. Int. J. of PRAI, 12(1):119–141, 1998.Google Scholar
  5. 5.
    D. Lopresti and A. Tomkins. On the searchability of electronic ink. In Proc. of the 4th Int. Workshop on Frontiers in Handwriting Recognition, pages 156–165, 1994.Google Scholar
  6. 6.
    M. Ma, P.S.P. Wang, D. Lopresti, and J. Crisman. Semantic matching of free-format Chinese handwriting. In Proc. of the 17th Int. Conf. on Comp. Proc. of Oriental Lang., pages 107–111, Hong Kong, April 1997.Google Scholar
  7. 7.
    R.B. Millward. Models of concept formation. In Aptitude, Learning, and Instruction. R.E. Snow et al (eds.). L. Erlbaum Assoc. Hillsdale, NJ, 1980.Google Scholar
  8. 8.
    H. Murase. On-line recognition system for free-format handwritten Japanese characters. In Character and Handwriting Recognition. P.S.P. Wang (ed.), pages 207–220. World Scientific, 1991.Google Scholar
  9. 9.
    I. Pavlidis, R. Singh, and N.P. Papanikcolopoulos. An on-line handwritten note recognition method using shape. In Proc. of the Int. Conf. on Document Analysis and Recognition, pages 914–918, 1997.Google Scholar
  10. 10.
    A. Poon, K. Weber, and T. Cass. Scribbler: A tool for searching digital ink. In Companion Proceedings of the CHI, pages 252–253, 1995.Google Scholar
  11. 11.
    D. Reynolds, D. Gupta, and R. Hull. Architectures for efficient scribble matching. In Proc. of the 4th Int. Workshop on Frontiers in Handwriting Recognition, pages 488–495, 1994.Google Scholar
  12. 12.
    C.C. Tappert. Speed, accuracy, and flexibility trade-offs in on-line character recognition. In Character and Handwriting Recognition. P.S.P. Wang (ed.), pages 79–96. World Scientific, 1991.Google Scholar
  13. 13.
    P.S.P. Wang. Learning, representation, understanding and recognition of words — an intelligent approach. In Fundamentals in Handwriting Recognition. S. Impedovo (ed.), pages 81–112. Springer-Verlag, 1994.Google Scholar
  14. 14.
    X.-H. Xiao and R.-W Dai. On-line handwritten Chinese characters recognition directed by components with dynamic templates. In Proc. of the 17th Int. Conf. on Comp. Proc. of Oriental Lang., pages 89–94, Hong Kong, April 1997.Google Scholar
  15. 15.
    S.L. Xie and M. Suk. On machine recognition of hand-printed Chinese characters by feature relaxation. Pattern Recognition, 21(1):l–7, 1988.CrossRefGoogle Scholar
  16. 16.
    K. Yamamoto and H. Yamada. Recognition of handprinted Chinese characters and Japanese cursive syllabary. In Proc. 7th ICPR, pages 385–388, Montreal, 1984.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Matthew Y. Ma
    • 1
  • Patrick S. P. Wang
    • 2
  1. 1.Panasonic Information and Networking Technologies LaboratoryPanasonic Technologies, Inc.PrincetonUSA
  2. 2.College of Computer ScienceNortheastern UniversityBostonUSA

Personalised recommendations