SVM-Based Selection of Colour Space Experts for Face Authentication

  • Mohammad T. Sadeghi
  • Samaneh Khoshrou
  • Josef Kittler
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4642)


We consider the problem of fusing colour information to enhance the performance of a face authentication system. The discriminatory information potential of a vast range of colour spaces is investigated. The verification process is based on the normalised correlation in an LDA feature space. A sequential search approach which is in principle similar to the “plus L and take away R” algorithm is applied in order to find an optimum subset of the colour spaces. The colour based classifiers are combined using the SVM classifier. We show that by fusing colour information using the proposed method, the resulting decision making scheme considerably outperforms the intensity based verification system.


Support Vector Machine Linear Discriminant Analysis Face Image Fusion Rule False Acceptance Rate 
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.


  1. 1.
    Berens, J., Finlayson, G.: Log-opponent chromaticity coding of colour space. In: Proceedings of the Fourth IEEE International Conference on Pattern Recognition, pp. 1206–1211. IEEE Computer Society Press, Los Alamitos (2000)Google Scholar
  2. 2.
    Colantoni, P., et al.: Color space transformations. Technical report,
  3. 3.
    Foley, J., van Dam, A., Feiner, S., Hughes, J.: Computer graphics: principles and practice, 2nd edn. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA (1996)zbMATHGoogle Scholar
  4. 4.
    Gevers, T., Smeulders, A.: Colour based object recognition. In: ICIAP, vol. 1, pp. 319–326 (1997)Google Scholar
  5. 5.
    Kawato, S., Ohya, J.: Real-time detection of nodding and head-shaking by directly detecting and tracking the ”between-eyes”. In: Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 40–45. IEEE Computer Society Press, Los Alamitos (2000)CrossRefGoogle Scholar
  6. 6.
    Kittler, J., Sadeghi, M.: Physics-based decorrelation of image data for decision level fusion in face verification. In: Roli, F., Kittler, J., Windeatt, T. (eds.) MCS 2004. LNCS, vol. 3077, pp. 354–363. Springer, Heidelberg (2004)Google Scholar
  7. 7.
    Marcel, S., Bengio, S.: Improving face verification using skin colour information. In: 16th International Conference on Pattern Recognition, vol. 2, pp. 20378–20382 (2002)Google Scholar
  8. 8.
    Ohta, Y., Kanade, T., Sakai, T.: Colour information for region segmentation. Computer Graphics and Image Processing 13(3), 222–241 (1980)CrossRefGoogle Scholar
  9. 9.
    Platt, J.: Sequential minimal optimization: A fast algorithm for training support vector machines. Technical Report 98-14, Microsoft Research, Redmond, Washington (April 1998)Google Scholar
  10. 10.
    Pudil, P., Novovicova, J., Kittler, J.: Floating search methods in feature selection. Pattern Recognition Letters 15, 1119–1125 (1994)CrossRefGoogle Scholar
  11. 11.
    Sadeghi, M., Khoshrou, S., Kittler, J.: Colour feature selection for face authentication. In: MVA 2007. Proceedings of the International Conference on Macine Vision Applications, Japan, May 2007 (2007)Google Scholar
  12. 12.
    Sadeghi, M., Khoshrou, S., Kittler, J.: Confidence based gating of colour features for face authentication. In: MCS 2007. Proceedings of the 7th International Workshop on Multiple Classifier System, Czech Republi, May 2007, pp. 121–130 (2007)Google Scholar
  13. 13.
    Sadeghi, M., Kittler, J.: A comparative study of data fusion strategies in face verification. In: The 12th European Signal Processing Conference, Vienna, Austria, 6-10 September 2004 (2004)Google Scholar
  14. 14.
    Sadeghi, M., Kittler, J.: Decision making in the LDA space: Generalised gradient direction metric. In: The 6th International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, May 2004, pp. 248–253 (2004)Google Scholar
  15. 15.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)zbMATHGoogle Scholar
  16. 16.
    Vertan, C., Cuic, M., Boujemaa, N.: On the introduction of a chrominance spectrum and its applications. In: Proceedings of the First International Conference on Colour in Graphics and Image Processing, 1-4 October 2000, pp. 214–218 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Mohammad T. Sadeghi
    • 1
  • Samaneh Khoshrou
    • 1
  • Josef Kittler
    • 2
  1. 1.Signal Processing Research Lab., Department of Electronics, University of Yazd, YazdIran
  2. 2.Centre for Vision, Speech and Signal Processing, School of Electronics and Physical Sciences, University of Surrey, Guildford GU2 7XHUK

Personalised recommendations