The Tangent Kernel Approach to Illumination-Robust Texture Classification

  • S. Verzakov
  • P. Paclík
  • R. P. W. Duin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)


Co-occurrence matrices are proved to be useful tool for the purpose of texture recognition. However, they are sensitive to the change of the illumination conditions. There are standard preprocessing approaches to this problem. However, they are lacking certain qualities. We studied the tangent kernel SVM approach as an alternative way of building illumination-robust texture classifier. Testing on the standard texture data has shown promising results.


  1. 1.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural Features for Image Classification.  3(6), 610–621 (November 1973)Google Scholar
  2. 2.
    Haralick, R.M.: Statistical and Structural Approaches to Texture. Proceedings of the IEEE 67, 786–804 (1979)CrossRefGoogle Scholar
  3. 3.
    Schölkopf, B.: Support Vector Learning. PhD thesis, Munich (1997)Google Scholar
  4. 4.
    Schölkopf, B., Simard, P.Y., Smola, A.J., Vapnik, V.N.: Prior knowledge in support vector kernels. In: Jordan, M.I., Kearns, M.J., Solla, S.A. (eds.) Advances in Neural Information Processing Systems, vol. 10, pp. 640–646. MIT Press, Cambridge (1998)Google Scholar
  5. 5.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (2000)zbMATHGoogle Scholar
  6. 6.
    USC-SIPI Image DatabaseGoogle Scholar
  7. 7.
    Schölkopf, B., Smola, A., Williamson, R.C., Bartlett, P.L.: New support vector algorithms. Neural Computation 12, 1207–1245 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • S. Verzakov
    • 1
  • P. Paclík
    • 1
  • R. P. W. Duin
    • 1
  1. 1.Information and Communication Theory Group Faculty of Electrical Engineering, Mathematics and Computer ScienceDelft University of TechnologyDelftThe Netherlands

Personalised recommendations