Independent Component Analysis and Support Vector Machine for Face Feature Extraction

  • Gianluca Antonini
  • Vlad Popovici
  • Jean-Philippe Thiran
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2688)


We propose Independent Component Analysis representation and Support Vector Machine classification to extract facial features in a face detection/localization context. The goal is to find a better space where project the data in order to build ten different face-feature classi fiers that are robust to illumination variations and bad environment conditions. The method was tested on the BANCA database, in different scenarios: controlled conditions, degraded conditions and adverse conditions.


Support Vector Machine Mutual Information Independent Component Analysis Face Detection Independent Component Analysis 
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]
    K.-K. Sung and T. Poggio. Learning human face detection in cluttered scenes. In V. Hlavac and R. Sara, editors, Computer Analysis of Images and Patterns, pages 432–439. Springer, Berlin, 1995.Google Scholar
  2. [2]
    Miroslav Hamouz, Josef Kittler, Jiri Matas, and Petr Bílek. Face detection by learned affine correspondences. LNCS, 2396:566–575, 2002.Google Scholar
  3. [3]
    A. Hyvaerinen and E. Oja. Independent component analysis: algorithms and applications. Neural Networks, 13(4–5):411–430, 2000.CrossRefGoogle Scholar
  4. [4]
    A. Hyvaerinen. Fast and robust fixed-point algorithms for independent component analysis. IEEE-NN, 10(3):626, May 1999.Google Scholar
  5. [5]
    H.M. Lades M. S. Bartlett and T. J. Sejnowski. Independent component representations for face recognition. In Proceedings of the SPIE, volume 3299, pages 528–539, 1998.Google Scholar
  6. [6]
    C. J.C. Burges. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2):121–167, 1998.CrossRefGoogle Scholar
  7. [7]
    S. Bengio, F. Bimbot, J. Mariéthoz, V. Popovici, F. Porée, E. Bailly-Baillière, G. Matas, and B. Ruiz. Experimental protocol on the BANCA database. IDIAPRR 05, IDIAP, 2002.Google Scholar
  8. [8]
    Chris Harris and Mike Stephens. A combined corner and edge detector. Proceedings Fourth Alvey Vision Conference, pages 147–151, 1988.Google Scholar
  9. [9]
    Michael S. Lewicki and Terrence J. Sejnowski. Learning overcomplete representations. Neural Computation, 12(2):337–365, 2000.CrossRefGoogle Scholar
  10. [10]
    Aapo Hyvärinen, Patrik O. Hoyer, and Mika Inki. Topographic independent component analysis. Neural Computation, 13(7):1527–1558, 2001.zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Gianluca Antonini
    • 1
  • Vlad Popovici
    • 1
  • Jean-Philippe Thiran
    • 1
  1. 1.Signal Processing Institute Swiss Federal Institute of Technology LausanneLausanneSwitzerland

Personalised recommendations