A New Knowledge Driven, Omnifont, Multiline OCR Process

  • Jose Paster
  • Evelina Zemelman


This paper describes a new knowledge-driven, multiline, omnifont, feature extraction OCR process. A new representation of the alphabet knowledge allows usage of a limited set of rules when building a character description, disregarding particularities of font style and size, and directs the recognition process to the creation of a specific limited set of hypotheses, and their consequent test and verification. The process, although tested mostly with printed characters, was designed with the possibility of extension to handprinted and handwritten characters.


Point Class Break Character Handwritten Character Alphabet Knowledge Vertex Class 
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.


  1. [1]
    J. R. Ullmann “Advances in Character Recognition” in “Applications of Pattern Recog ”(K. S. Fu, ed.), pp. 197–236, CRC Press, Inc., Florida, 1982.Google Scholar
  2. [2]
    C. Y. Suen “Character Recognition by Computer and Applications” in “Handbook of Patters Recognition and Image Processing” (Y. T. Young, K. S. Fu, ed.), pp. 569–586, Academic Press, Inc., 1986.Google Scholar
  3. [3]
    M. Shridhar, A. Badreldin “High Accuracy Character Recognition Algorithm using Fourier and Topological Descriptors”, Patters Recognition, Vol. 17, #5, 1984, p. 515.MATHCrossRefGoogle Scholar
  4. [4]
    R. M. K. Sinha “A Knowledge Based Script Reader”, Proceedings of 7th Int. Conf. on Pattern Recognition, Montreal, Canada, 198, p. 763.Google Scholar
  5. [5]
    R. Rozinovic, S. N. Srihari “Knowledge Based Cursive Script Interpretation”, Proceedings of 7th Int. Conf. on Pattern Recognition, Montreal, Canada, 198, p. 774.Google Scholar
  6. [6]
    J. Pastor, E. Zemelman. “Knowledge Representation of Alphanumerics in Terms of Graph Theory, and its Application to a New Omnifont OCR Process”, II Inter Sympo on Knowledge Engineering, Madrid, Spain, 1987.Google Scholar
  7. [7]
    K. Koffka. Koffka “Principles of Gestalt Psychology”, p. 110, Harcourt, Brace & World, NY 1935.Google Scholar
  8. [8]
    J. Pastor “Image Thinning Process”, US Patent 4539704, Sept. 3, 1985Google Scholar
  9. [9]
    J. Pastor, H. L. Parker, D. H. Wilson “Real Time Character Thinning Process”, US Patent 4574357, March 4, 1986Google Scholar
  10. [10]
    Watanabe, Satosi,“Pattern Recognition, Human and Mechanical”, p. 443, John Willey & Sons, Inc. NY, 1985.Google Scholar
  11. [11]
    J. P. Frisby. Frisby “Seeing, Illusion, Brain and Mind”, p. Ill, Oxford University Press, 1980.Google Scholar
  12. [12]
    Kahans S., Pavlidis T. and Baird H., IEEE; PAM 1–9, 2, 274, 1987 use also thinned stroke characters as primitives.Google Scholar

Copyright information

© Plenum Press, New York 1988

Authors and Affiliations

  • Jose Paster
    • 1
  • Evelina Zemelman
    • 1
  1. 1.Corporate Engineering and Technology DivisionPitney Bowes, Inc.StamfordUSA

Personalised recommendations