Crucial combinations for the recognition of handwritten letters

  • C. Y. Suen
  • Z. C. Li
Invited Talks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1339)


Crucial features are important for the identification of patterns. Great efforts have been devoted to discover the most distinctive features. This paper presents the ideas of splitting patterns into 4- or 6- parts, integration for recognition, and selection of crucial combinations. The crucial combinations are explored with particular reference to 26 handprinted letters of the English alphabet. This paper proposes a new and simple algorithm to perform the crucial combinations. Also, the largest confusion regions and algorithms for finding them are provided. The most useful crucial combinations and the largest confusion combinations are listed in this paper.

Key words

Character recognition handwritten characters alphabetic handprints recognition rate regional decomposition method part combination crucial part crucial combination confusion combination 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Z. C. Li and C. Y. Suen, “Basic crucial combinations of parts to handprinted characters,” Technical Report, Department Applied Mathematics, National Sun Yat-sen University, Kaohsiung, Taiwan, 1997.Google Scholar
  2. [2]
    Z.C. Li, C.Y. Suen and J. Guo, “A regional decomposition method for recognising handprinted characters,” IEEE Trans Syst. Man and Cybern., vol. 25, pp.988–1010, 1995.Google Scholar
  3. [3]
    Z.C. Li, C.Y. Suen and J. Guo, “Hierarchical models for analysis and recognition of handwritten characters,” Annals of Mathematics and Artificial Intelligence Vol. 10, pp.149–174, 1994.Google Scholar
  4. [4]
    C.Y. Suen, J. Guo and Z.C. Li, “Analysis and recognition of alphanumeric handprints by parts,” IEEE Trans. on Sys. Man and Cybern., Vol.24, pp.614–631, 1994.Google Scholar
  5. [5]
    C.Y. Suen et al, Canadian standard alphanumeric character set for handprinting, Z243.34-M1983, Canadian Standards Association, Toronto, 1983.Google Scholar
  6. [6]
    C.Y. Suen (Ed.), Frontiers in Handwriting Recognition, CENPARMI, Concordia University, 1990.Google Scholar
  7. [7]
    P.S. P. Wang (Ed.), Character & Handwriting Recognition: Expanding Frontiers, World Scientific, Singapore, 1991.Google Scholar
  8. [8]
    P.A. Koles, “Clues to letters recognition implications for the design of characters,” J. Typographical Research, Vol. 3, no. 2, pp.145–168, 1968.Google Scholar
  9. [9]
    S. Impedovo and G. Dimauro, “An interactive system for the selection of handwritten numeral classes,” Proc. 10th International Conference on Pattern Recognition, Atlantic City, New Jersey, June 1990, pp. 563–566.Google Scholar
  10. [10]
    C. Nadal, R. Legault and C.Y. Suen, “Complementary algorithms for the recognition of totally unconstrained handwritten numerals,rd Ibid, pp. 443–449.Google Scholar
  11. [11]
    V. K. Govindan and A. P. Shivaprasad, “Character recognition — a review,” Pattern Recognition, Vol. 23, pp.671–683, 1990.Google Scholar
  12. [12]
    J. Mantas, “An overview of character recognition methodologies,” Pattern Recognition, Vol. 19, pp.425–430, 1986.Google Scholar
  13. [13]
    R. Kasturi and L. O'Gorman, “Document image analysis: a bibliography,” Machine Vision and Applications, An International Journal, Vol. 5, pp.231–243, 1992.Google Scholar
  14. [14]
    H. Bunke and A. Sanfeliu, Syntactic and Structural Pattern Recognition Theory and Applications, World Scientific, Singapore, 1990.Google Scholar
  15. [15]
    R. Lindwurm, T. Breuer and K. Kreuzer. “Multi-expert system for handprint recognition,” ] Proc. 5th Int. Workshop on Frontiers in Handwriting Recognition, pp. 125–129, Sept. 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • C. Y. Suen
    • 1
  • Z. C. Li
    • 2
  1. 1.Centre for Pattern Recognition and Machine IntelligenceConcordia UniversityQuebecCanada
  2. 2.Department of Applied MathematicsNational Sun Yat-sen UniversityKaohsiungTaiwan

Personalised recommendations