Face recognition: The problem of compensating for changes in illumination direction

  • Yael Moses
  • Yael Adini
  • Shimon Ullman
Recognition I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)


Recognizing faces is a difficult problem due to the generally similar shape of faces combined with the considerable variability in images of the same face under different viewing conditions. In this paper we consider image variation due mainly to illumination conditions. We study several image representations that are often considered insensitive to changes of illumination conditions, such as edge maps, derivatives of the grey-level image, and the image convolved with Gabor filters. For each of these representations, we compare the differences between images of the same face under different imaging conditions, with differences between images of distinct faces. The comparison is performed using a controlled database of faces, in which each of the imaging parameters (illumination, viewing position, and expression) is controlled separately. The main result of these studies is that the variations between the images of the same face due to illumination and viewing directions are almost always larger than image variations due to a change in face identity. For illumination changes, this reversal is almost complete except for representations that emphasized the horizontal features. However, even for these representations, systems based only on comparing such representations will fail to recognize up to 30% of the faces in our database. We conclude that these representations are insufficient by themselves to overcome the variation between images due to changes in illumination direction as well as changes due to viewing position and expression.


Face Recognition Imaging Parameter Human Visual System Frontal View Illumination Condition 
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. Adini, Y., Moses, Y., and Ullman, S. (1993). Face recognition: the problem of compensating for illumination changes. Technical report cc93-21, The Weizmann Institute of Science.Google Scholar
  2. Bruce, V. (1982). Changing faces: visual and non visual coding processes in face recognition. British Journal of Psychology, 73:105–116.Google Scholar
  3. Brunelli, R. and Poggio, T. (1991). Hyper BF networks for real object recognition. In Proceedings IJCAI, pages 1278–1284, Sydney, Australia.Google Scholar
  4. Buhmann, J., Lades, M., and Eeckman, F. (1993). A silicon retina for face recognition. Technical Report No. 8596-CS, Institut für Informatik, Universität Bonn.Google Scholar
  5. Burns, J., Weiss, R., and Riseman, E. (1992). The non-existence of general-case view-invariants. In Mundy, J. and Zisserman, A., editors, Geometrical Invariance in Computer Vision. M.I.T. press.Google Scholar
  6. Canny, J. F. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8:679–698.Google Scholar
  7. Clemens, D. and Jacobs, D. (1991). Model-group indexing for recognition. In Proc. CVPR-91, and IEEE Trand PAMI vol 13, No 10 p. 1007–1017.Google Scholar
  8. Daugman, J. G. (1984). Spatial visual channels in the fourier plane. Vision Res., 24(9):891–910.Google Scholar
  9. Daugman, J. G. (1987). Image analysis and compact coding by oriented 2d gabor primitives. SPIE processing, 758:19–30.Google Scholar
  10. Davies, G. M., Ellis, H., and Shephered, J. W. (1978). Face recognition accuracy as a function of mode of representation. Journal of Applied Psychology, 92:507–523.Google Scholar
  11. Davis, L. S. (1975). A survey of edge detection techniques. Computer Graphics and Image Processing, 4:248–270.Google Scholar
  12. De-Valios, R. and De-Valios, K. (1988). Spatial Vision. Oxford Univ. Press, New York.Google Scholar
  13. Deriche, R. (1987). Optimal edge detection using recursive filtering. In proc. ICCV, London, pages 501–504.Google Scholar
  14. Edelman, S., Reisfeld, D., and Yeshurun, Y. (1992). A system for face recognition that learns from examples. In Sandini, S., editor, Proc. European Conference on Computer Vision, pages 787–791. Springer-Verlag.Google Scholar
  15. Govindaraju, V., Sher, D. B., Srihari, R., and Srihari, S. N. (1989). Locating human faces in newspaper photographs. In Proc. CVPR 89, pages 549–554.Google Scholar
  16. Haralick, R. M. (1984). Digital step edges from zero crossings of second directional derivatives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6:58–68.Google Scholar
  17. Horn, B. K. P. and Brooks, M. (1989). Seeing shape from shading. MIT Press, Cambridge, Mass.Google Scholar
  18. Kanade, T. (1977). Computer recognition of human faces. Birkhauser Verlag. Basel ans Stuttgart.Google Scholar
  19. Manjunath, B., Shekhar, C., Chellappa, R., and von der Malsburg, C. (1992). A robust method for detecting image features with application to face recognition and motion correspondence. In ICPR B, pages 208–212.Google Scholar
  20. Marr, D. and Hildreth, E. (1980). Theory of edge detection. Proc. R. Soc. Lond. B, 207:187–217.Google Scholar
  21. Mercelja, S. (1980). Mathematical description of the responses of simple cortical cells. J. Opical Soc., 70:1297–1300.Google Scholar
  22. Moses, Y. (1993). Face recognition: generalization to novel images. PhD thesis, Weizmann Institute of Science.Google Scholar
  23. Moses, Y., Edelman, S., and Ullman, S. (1993). Generalization to novel images in upright and inverted faces. Technical report cc93-14, The Weizmann Institute of Science.Google Scholar
  24. Moses, Y. and Ullman, S. (1992). Limitation of non-model-based recognition schemes. In Sandini, G., editor, Proc. ECCV-92, pages 820–828. Springer-Verlag.Google Scholar
  25. Patterson, K. and Baddeley, A. (1977). When face recognition fails. Journal of Experimental Psychology: Human Learning and Memory, 3:406–417.Google Scholar
  26. Pollen, D. and Ronner, S. (1983). Visual cortical neurons as localized spatial frequency filters. IEEE Transactions on System, Man and Cybernetics, SMC-13, pages 907–916.Google Scholar
  27. Reisfeld, D. and Yeshurun, Y. (1992). Robust detection of facial features by generalized symmetry. In ICPR A, pages 117–120.Google Scholar
  28. Shen, J. and Castan, S. (1987). An optimal linear operator for edge detection. In Proc. SPIE-87.Google Scholar
  29. Shepherd, J., Davies, G., and Ellis, H. (1981). Studies of cue saliency. In Davies, G. M., Ellis, H., and Shepherd, J., editors, Perceiving and Recognizing Faces, pages 104–131. Academic Press.Google Scholar
  30. Torre, V. and Poggio, T. (1986). On edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8:147–163.Google Scholar
  31. Ullman, S. and Basri, R. (1991). Recognition by linear combinations of models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13:992–1005.Google Scholar
  32. Watson, A. and Robson, J. (1981). Discrimination at threshold: Labeled detectors in human vision. Vision Research, 19:19–32.Google Scholar
  33. Wilson, H. R. and Bergen, J. R. (1979). A four mechanism model for threshold spatial vision. Vision Research, 19:19–32.Google Scholar
  34. Wong, K., Law, H., and Tsang, P. (1989). A system for recognising human faces. In Proc. ICASSP, pages 1638–1642.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Yael Moses
    • 1
  • Yael Adini
    • 1
  • Shimon Ullman
    • 1
  1. 1.Department of Applied Mathematics and Computer ScienceThe Weizmann Institute of ScienceRehovotIsrael

Personalised recommendations