A heuristic algorithm for stroke extraction

  • Xiaofeng Yin
  • Dongzhuang Su
Document Processing
Part of the Lecture Notes in Computer Science book series (LNCS, volume 301)


An algorithm for extraction of strokes of handwritten and printed Chinese characters is described. The main idea is based on the heuristic information of Chinese character structure. Experiment shows that strokes can be extracted efficiently according to the heuristic strategy. The general distribution of terminal points is analysed by means of Polya's theorem. The improved algorithm in speed by combining the stroke extraction with thinning is also discussed.


Chinese Character Terminal Point Black Pixel Heuristic Strategy Heuristic Information 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

10. References

  1. (1).
    X.F. Yin, C.D. Yan, D.Z. Su. "Feature extraction and distribution of a primary Chinese character set". Journal of Chinese information Processing. Vol.1, No.1, 1986.Google Scholar
  2. (2).
    X.Z.Chang, etc. "The automatic recognition of handprinted Chinese character-a method of extracting an ordered sequences of strokes" Pattern Recognition Letters 1. 1983.Google Scholar
  3. (3).
    Leow Wee-Kheng. "Syntactic approach to Chinese character recognition". Proc. of ICCC'86. Singapore.Google Scholar
  4. (4).
    C.Y. Suen etc. "Advances in recognition of handwritten characters". Proc. of ICPR. 1978.Google Scholar
  5. (5).
    D.B. Lenat. "The nature of heuristics". Artificial Intelligence. No.4 Vol. 20. 1983.Google Scholar
  6. (6).
    D.I.A. Cohen. "Basic Techniques of Combinatorial Theory". John Wiley & Sons. 1978.Google Scholar
  7. (7).
    Fang-hsuan Cheng etc. "Three stroke extraction methods for recognition of handwritten Chinese characters". Proc. of TCCC'86. Singapore.Google Scholar
  8. (8).
    Xiaofeng Yin etc. "A quick thinning algorithm for Chinese characters". Proc. of 2nd National Conference on Computer Graphics and Pattern Recognition. 1986.Google Scholar
  9. (9).
    Theo Pavlidis. "Algorithms for Graphics and Image Processing". Computer Science Press. 1982.Google Scholar
  10. (10).
    Xiaofeng Yin, Dongzhuang Su. "Stroke Analysis of Handwritten Chinese character by Regression Method" Proc. of ICCIP'87, Vol.2, Beijing.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • Xiaofeng Yin
    • 1
  • Dongzhuang Su
    • 1
  1. 1.Beijing Information Technology InstituteWeizikeng Dewai BeijingP.R. of China

Personalised recommendations