Illumination Normalized Face Image for Face Recognition

  • Jaepil Ko
  • Eunju Kim
  • Heyran Byun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)


A small change in illumination produces large changes in appearance of face even when viewed in fixed pose. It makes face recognition more difficult to handle. To deal with this problem, we introduce a simple and practical method based on the multiple regression model, we call it ICR (Illumination Compensation based on the Multiple Regression Model). We can get the illumination-normalized image of an input image by ICR. To show the improvement of recognition performance with ICR, we applied ICR as a preprocessing step. We achieved better result with the method in preprocessing point of view when we used a popular technique, PCA, on a public database and our database.


  1. 1.
    Michael J. Tarr, Daniel Kersten, Heinrich H. Bulthoff,: Why the visual recognition system might encode the effects of illumination, Pattern Recognition (1998)Google Scholar
  2. 2.
    Yael Adini, Yael Moses, and Shimon Ullman,: Face Reconition: The problem of Compensating for Changes in Illumination Direction, IEEE Trans. on PAMI Vol. 19, No. 7(1997)721–732Google Scholar
  3. 3.
    P. J. Phillips, H. Moon, P. Rauss, and S. A. Rizvi.: The FERET Evaluation Methodology for Face-Recognition Algorithms. IEEE Conference on CVPR, Puerto Rico (1997) 137–143Google Scholar
  4. 4.
    S. Rizvi, P. Phillips, and H. Moon.: The FERET verication testing protocol for face recognition algorithms. IEEE Conference on Automatic Face-and Gesture-Recognition (1998) 48–53Google Scholar
  5. 5.
    R. Chellappa and W. Zhao,: Face Recognition: A Literature Survey. ACM Journal of Computing Surveys (2000)Google Scholar
  6. 6.
    A. Yuille, D. Snow, R. Epstein, P. Belhumeur,: Determining Generative Models of Objects Under Varying Illumination: Shape and Albedo from Multiple Images Using SVD and Integrability, International Journal of Computer Vision, 35 (3X1999) 203–222Google Scholar
  7. 7.
    P. N. Belhumeur and D. J. Kriegman.: What is the set of images of an object under all possible lighting conditions?, IEEE Conference on CVPR (1996)Google Scholar
  8. 8.
    Athinodoros S. Georghiades, David J. Kriegman, Peter N. Belhumeur,: Illumination Cones for Recognition Under Variable Lighting: Faces, IEEE Conference on CVPR (1998) 52–58Google Scholar
  9. 9.
    M. Turk and A. Pentland,: Eigenfaces for recognition. Journal of Cognitive Neuroscience, Vol 3 (1991)Google Scholar
  10. 10.
    V. Belhumeur, J. Hespanha, and D. Kriegman.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans. on PAMI (1997) 711–720Google Scholar
  11. 11.
    Bischof, H.; Wildenauer, H.; Leonardis, A.: Illumination insensitive eigenspaces, IEEE Conference on Computer Vision, Vol. 1 (2001) 233–238Google Scholar
  12. 12.
    Wen Yi Zhao; Chellappa, R.: Illumination-Insensitive Face Recognition Using Symmetric Shape-from-Shading, IEEE Conference on CVPR, Vol. 1, (2000) 286–293Google Scholar
  13. 13.
    S. M. Ross,: Introduction to Probability and Statistics for Engineers and Scientists, Wiley, New York (1987)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Jaepil Ko
    • 1
  • Eunju Kim
    • 1
  • Heyran Byun
    • 1
  1. 1.Dept. of Computer ScienceYonsei Univ.SeoulKorea

Personalised recommendations