Eigenlights: Recovering Illumination from Face Images

  • James Burnstone
  • Hujun Yin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6936)


In this paper, we present the use of subspace modelling to find the basis features of illumination across human face images. Instead of using a real image data set we use computer-generated 3D models, which we have built. Using these models we can better investigate the effect of the recognition of faces under illumination not confined within a particular trained subset. With this we have designed a recognition system where we investigate how many training images are necessary to build an illumination subspace that gives robust recognition. We aim to apply this technique to deal with the lighting problem in face recognition on mobile devices where some current methods are simply too complex to use.


Face Recognition Face Image Illumination Condition Point Light Source Face Space 
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.
    Blanz, V., Romdhani, S., Vetter, T.: Face identification across different poses and illumination with a 3D morphable model. In: Proc. 5th Int’l Conf. Automatic Face and Gesture Recognition, pp. 192–197 (2002)Google Scholar
  2. 2.
    Zhang, L., Samaras, D.: Face recognition from a single image under arbitrary unknown lighting using spherical harmonics. IEEE Trans. Pattern Analysis and Machine Intelligence 28, 209 (2006)CrossRefGoogle Scholar
  3. 3.
    Belhumeur, P.N., Kriegman, D.J.: What is the set of images of an objects under all possible illumination conditions? Internal Journal of Computer Vision 28(3), 245–260 (1998)CrossRefGoogle Scholar
  4. 4.
    Basri, R., Jacobs, D.W.: Lambertian reflectance and linear subspaces. IEEE Trans. Pattern Analysis and Machine Intelligence 25(2), 218–233 (2001)CrossRefGoogle Scholar
  5. 5.
    Lee, K., Ho, J., Kriegman, D.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. Pattern Analysis and Machine Intelligence 27(5), 684–695 (2005)CrossRefGoogle Scholar
  6. 6.
    Shim, H., Luo, J., Chen, T.: A subspace model-based approach to face relighting under unknown lighting and pose. IEEE Trans. on Image Processing 17(8), 1331–1341 (2008)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Wang, Y., Liu, G., Wen, Z., Zhang, Z., Samaras, D.: Face re-lighting from a single image under harsh lighting conditions. IEEE Trans. Pattern Analysis and Machine Intelligence 31(11), 1968–1984 (2009)CrossRefGoogle Scholar
  8. 8.
    Ramamoorthi, R., Hanrahan, P.: On the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian object. J. Optical Soc. Am, A. 18(10), 2448–2459 (2001)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. J. Cognitive Neuroscience 3(1), 71–86 (1991)CrossRefGoogle Scholar
  10. 10.
    Ramamoorthi, R.: Analytic PCA construction for theoretical analysis of lighting variability in images of a Lambertian object. IEEE Trans. Pattern Analysis and Machine Intelligence 24(10), 1322 (2002)CrossRefGoogle Scholar
  11. 11.
    Delac, K., Grgic, M., Kos, T.: Sub-image homomorphic filtering for improving facial identification under difficult illumination conditions. In: Int’l Conf. on Systems, Signals and Image Processing, Budapest (2006) Google Scholar
  12. 12.
    Edwards, G.J., Lanitis, A., Taylor, C., Cootes, T.: Statistical models of face images – improving specificity. Image and Vision Computing 16, 203–211 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • James Burnstone
    • 1
  • Hujun Yin
    • 1
  1. 1.School of Electrical and Electronic EngineeringThe University of ManchesterUK

Personalised recommendations