Hierarchical Backward Search Method: A New Classification Tree Using Preprocessing by Multilayer Neural Network

  • Hiroto Yoshii
Conference paper


This paper proposes a novel pattern recognition algorithm. The new algorithm consists of two stages: the pyramid making stage and the classification making stage. The classification tree generated by the algorithm is called “PACT” (Pyramid Architecture Classification Tree), which is just a kind of classification tree but has a great ability to deal with huge dimensional real scale problem.

PACT does not only shows good performance but also induces a new idea: a fractal characteristic which a category set shows in huge dimensional feature space. The new idea accounts for how awkward conventional algorithms, including neural networks and classification trees, are when applied to huge dimensional pattern classification problems. The new idea gives a new positive reason for hierarchical pattern processing.


Recognition Rate Classification Tree Fractal Characteristic Training Pattern Pattern Recognition Algorithm 
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.
    Russel Reed: IEEE Trans. NN 4 (5), 740 (1993)CrossRefGoogle Scholar
  2. 2.
    L. Breiman, J; H. Friedman, R. A. Olshen, and C. J. Stone: Classification and Regression Trees. Belmont CA: Wadsworth 1984.Google Scholar
  3. 3.
    J. M. Jolion and A. Rosenfeld: A Pyramid Framework for Early Vison. Netherlands: Kluwer Academic Publishers 1994.CrossRefGoogle Scholar
  4. 4.
    S. R. Safavian and D. Landgrebe: IEEE Trans. SMAC 21(3) 660(1991)Google Scholar
  5. 5.
    S. J. Smith, M. O. Bourgoin, K. Sims, and H. L. Voorhees: IEEE Trans. PAMI 16 (9) 915 (1994)CrossRefGoogle Scholar
  6. 6.
    J. A. Sirat and J. P. Nadal: Network 1 423 (1990)MathSciNetCrossRefGoogle Scholar
  7. 7.
    A. Sankar and R. J. Mammone: Neural Networks: Theory and Applications. 281, New York: Academic Press 1991.Google Scholar
  8. 8.
    H. Guo and S. B. Gelfand: IEEE Trans. NN 3 (6) 923 (1992)CrossRefGoogle Scholar
  9. 9.
    I. K. Sethi and J. H. Yoo: Pattern Recognition 27 (7) 939 (1994)CrossRefGoogle Scholar
  10. 10.
    J. Zhou and T. Pavlidis: Pattern Recognition 27 (11) 1539 (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Hiroto Yoshii
    • 1
  1. 1.Media Technology LaboratoryCanon Inc.Kashimada Saiwai-ku Kawasaki-shi Kanagawa 211Japan

Personalised recommendations