Fisher Light-Fields for Face Recognition across Pose and Illumination

  • Ralph Gross
  • Iain Matthews
  • Simon Baker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2449)


In many face recognition tasks the pose and illumination conditions of the probe and gallery images are different. In other cases multiple gallery or probe images may be available, each captured from a different pose and under a different illumination. We propose a face recognition algorithm which can use any number of gallery images per subject captured at arbitrary poses and under arbitrary illumination, and any number of probe images, again captured at arbitrary poses and under arbitrary illumination. The algorithm operates by estimating the Fisher light-field of the subject’s head from the input gallery or probe images. Matching between the probe and gallery is then performed using the Fisher light-fields.


Face Recognition Linear Discriminant Analysis Probe Image Illumination Condition Gesture Recognition 
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.
    Pentland, A., Moghaddam, B., Starner, T.: View-based and modular eigenspaces for face recognition. In: Proc. of CVPR. (1994)Google Scholar
  2. 2.
    Murase, H., Nayar, S.: Visual learning and recognition of 3-D objects from appearance. IJCV 14 (1995) 5–24CrossRefGoogle Scholar
  3. 3.
    Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: Generative models for recognition under variable pose and illumination. In: Proc. of the 4th Conf. on Face and Gesture Recognition. (2000)Google Scholar
  4. 4.
    Belhumeur, P., Hespanha, J., Kriegman, D.: Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. IEEE PAMI 19 (1997) 711–720Google Scholar
  5. 5.
    Batur, A., Hayes, M.: Linear subspaces for illumination robust face recognition. In: Proc. of the 2001 CVPR,. (2001)Google Scholar
  6. 6.
    Blanz, V., Romdhani, S., Vetter, T.: Face identification across different poses and illumination with a 3d morphable model. In: Proc. of the 5th Conf. on Face and Gesture Recognition. (2002)Google Scholar
  7. 7.
    Levoy, M., Hanrahan, M.: Light field rendering. In: Proc. of SIGGRAPH. (1996)Google Scholar
  8. 8.
    Leonardis, A., Bischof, H.: Dealing with occlusions in the eigenspace approach. In: Proc. of CVPR. (1996)Google Scholar
  9. 9.
    Black, M., Jepson, A.: Eigen-tracking: Robust matching and tracking of articulated objects using a view-based representation. IJCV 36 (1998) 101–130Google Scholar
  10. 10.
    Adelson, E., Bergen, J.: The plenoptic function and elements of early vision. In Landy, Movshon, eds.: Computational Models of Visual Processing. MIT Press (1991)Google Scholar
  11. 11.
    Turk, M., Pentland, A.: Face recognition using eigenfaces. In: CVPR. (1991)Google Scholar
  12. 12.
    Gortler, S., Grzeszczuk, R., Szeliski, R., Cohen, M.: The lumigraph. In: SIG-GRAPH. (1996)Google Scholar
  13. 13.
    Gross, R., Baker, S., Matthews, I.: Eigen light-fields and face recognition across pose. In: Proc. of the 5th Conf. on Face and Gesture Recognition. (2002)Google Scholar
  14. 14.
    Vetter, T., Poggio, T.: Linear object classes and image synthesis from a single example image. IEEE Trans. on PAMI 19 (1997) 733–741Google Scholar
  15. 15.
    Fukunaga, K.: Introduction to statistical pattern recognition. Academic Press (1990)Google Scholar
  16. 16.
    Zhao, W., Krishnaswamy, A., Chellappa, R., Swets, D., Weng, J.: Discriminant Analysis of Principal Components for Face Recognition. In: Face Recognition: From Theory to Applications. Springer Verlag (1998)Google Scholar
  17. 17.
    Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression (PIE) database. In: Proc. of the 5th Conf. on Face and Gesture Recognition. (2002)Google Scholar
  18. 18. Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Ralph Gross
    • 1
  • Iain Matthews
    • 1
  • Simon Baker
    • 1
  1. 1.The Robotics InstituteCarnegie Mellon UniversityPittsburgh

Personalised recommendations