Invariant Reference Points Methodology and Applications

  • Krystian Ignasiak
  • Władysław Skarbek
  • Miloud Ghuwar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)


A methodology for pattern recognition based on design of invariant reference points is described. Within this framework many classical pattern classifiers can be described (e.g. the k-NN distance classifier) and few new classifiers are defined (e.g. LPCAS classifier). LPCAS is applied for handwritten digit recognition reaching performance of 99.4% of recognition rate on NIST database.


Reference Point Recognition Rate Selection Technique Subspace Method Source Domain 
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.
    C. Bishop (1995) Neural Networks for Pattern Recognition, Clarendon Press, Oxford.Google Scholar
  2. 2.
    K.I. Diamantaras, S.Y. Kung (1996) Principal Component Neural Networks, John Wiley & Sons, New York.zbMATHGoogle Scholar
  3. 3.
    R.O. Duda, P.E. Hart (1973) Pattern Classification and Scene Analysis, Wiley, New York.zbMATHGoogle Scholar
  4. 4.
    Y. Fisher, ed. (1995) Fractal Image Compression — Theory and Application, Springer Verlag.Google Scholar
  5. 5.
    H. Hotelling (1933) Analysis of a complex of statistical variables into principal components, Journal of Educational Psychology 24, 417–441.CrossRefGoogle Scholar
  6. 6.
    T. Kohonen (1995) Self-Organizing Maps, Springer, Berlin.Google Scholar
  7. 7.
    Y. Linde, A. Buzo, R.M. Gray (1980) An algorithm for vector quantizer design, IEEE Trans. Comm., COM-28 1980 28–45.Google Scholar
  8. 8.
    E. Oja (1983) Subspace methods of pattern recognition, Research Studies Press, England.Google Scholar
  9. 9.
    B.D. Ripley (1996) Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge.zbMATHGoogle Scholar
  10. 10.
    Skarbek, W.: Local Principal Components Analysis for Transform Coding. 1996 Int. Symposium on Nonlinear Theory and its Applications, NOLTA'96 Proceedings, Research Society NTA, IEICE, Japan, Oct. 1996 381–384Google Scholar
  11. 11.
    Skarbek, W., Ghuwar, M., Ignasiak, K.: Local Subspace Method for Pattern Recognition. CAIP'97, Lecture Notes 1296, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Krystian Ignasiak
    • 1
  • Władysław Skarbek
    • 1
  • Miloud Ghuwar
    • 1
  1. 1.Multimedia Laboratory, Department of Electronics and Information TechnologyWarsaw University of TechnologyUSA

Personalised recommendations