COGNITUS — Fast and reliable recognition of handwritten forms based on vector quantisation

  • Martin Neschen
  • Frank Nübel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1067)


We report on an efficient intelligent character recognition tool for the automatic treatment of handwritten bank transfer forms. The classification is based on nearest-neighbor algorithms and a novel binary clustering technique for the generation of large prototype sets. We introduce a new confidence measure which can be used on a decision tree structure to combine lowest error rates with a very high recognition speed. Likelihood vectors allow context correction by database queries based on dynamic programming techniques as well as an easy integration of different classifier approaches in a multi-agent environment. In this paper, we present all components of the prototype system and give details on its realization and on possible parallel implementations on embedded systems.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Y. Le Cun et al., “Handwritten Zip Code Recognition with Multilayer Networks”, Proc. of the 10th Int. Conf. on Pattern Recognition, IEEE, Comp. Soc. Press (1990)Google Scholar
  2. 2.
    P. Simard, Y. Le Cun, J. Denker, “Efficient Pattern Recognition Using a New Transformation Distance”, Neural Information Processing Systems, vol. 5, p. 50 (1993)Google Scholar
  3. 3.
    T. M. Cover, P. E. Hart, “Nearest neighbor pattern classification”, IEEE Trans. Info. Theory, IT-13, p. 21 (1967)Google Scholar
  4. 4.
    R. O. Duda, P. E. Hart, “Pattern Classification and Scene Analysis”, J. Wiley & Sons, New York, 1973Google Scholar
  5. 5.
    M. Neschen, M. Gumm, “A Scalable Bit-Sequential SIMD Array for Pattern Recognition and Neural Networks”, Proceedings of the PARLE'94 conference, Springer Verlag, Berlin (1994)Google Scholar
  6. 6.
    M. D. Garris, R. A. Wilkinson, NIST Special Database 3: Handwritten Segmented Characters, National Institute of Standard and Technology, (1992)Google Scholar
  7. 7.
    J. MacQueen, “Some methods for classification and analysis of multivariate observations”, Proc. of the Fifth Berkeley Symposium on Math. Stat. and Prob., vol. 1, 281 (1967)Google Scholar
  8. 8.
    L. Montoliu, “Handwritten Word Recognition by a Multi-Agent System: Preliminary Results”, I.E.E. European Workshop on ”Handwriting analysis and recognition”, p 4.1, Brussels, 12–13 July 94Google Scholar
  9. 9.
    M. Neschen, “Vector Quantisation Classifiers for Handwritten Character Recognition”, Proc. of the ZEUS-95 Workshop, Linkoping, Sweden, May 1995, p. 138, IOS Press, NetherlandsGoogle Scholar
  10. 10.
    V.I. Levenshtein, “Binary Codes Capable of Correcting Deletions, Insertions, and Reversals”, Soviet Physics — Doclady, vol. 10, p. 707 (1965)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Martin Neschen
    • 1
  • Frank Nübel
    • 1
  1. 1.Zentrum für Paralleles Rechnen (ZPR)Universität zu KölnKölnGermany

Personalised recommendations