A Fast Method of Lighting Estimate Using Multi-linear Algebra

  • Yuequan Luo
  • Guangda Su
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3338)


Natural facial images are the composite consequence of multiple factors and illumination is an important one. In many situations, we must normalize the facial image’s illumination or simulate the similar lighting condition; therefore, accurate estimation of the facial image’s lighting is necessary and can help get a good result. Because of its richer representational power, multi-linear algebra offers a potent mathematical framework for analyzing the multifactor structure of image ensembles. We apply multi-linear algebra to obtain a parsimonious representation of facial image ensembles which separates the illumination factor from facial images. With the application of multi-linear algebra, we can avoid not only the use of 3D face model, but also that of the complicated iterative algorithm, thus we obtain a fast and simple method of lighting estimation.


Lighting estimate multi-linear algebra 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Moses, Y., Adini, Y., Ullman, S.: Face Recognition: The Problem of Compensating for Changes in Illumination Direction. In: Proc. European Conf. Computer Vision, pp. 286–296 (1994)Google Scholar
  2. 2.
    Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination. In: IEEE Conf. on Automatic Face and Gesture Recognition, March 2000, pp. 277–284 (2000) (oral presentation)Google Scholar
  3. 3.
    Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. In: IEEE Trans. on Pattern Analysis and Machine Intelligence, June 2001, pp. 643–660 (2001)Google Scholar
  4. 4.
    Zhao, W., Chellappa, R.: Illumination-Insensitive Face Recognition Using Symmetric Shape-from-Shading. In: Computer Vision and Pattern Recognition (CVPR 2000), June 13 - 15, vol. 1, p. 1286 (2000)Google Scholar
  5. 5.
    Shashua, A., Riklin-Raviv, T.: The Quotient Image: Class-Based Re-rendering and Recognition with Varying Illuminations. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23(2) (February 2001)Google Scholar
  6. 6.
    Alex, M., Vasilescu, O., Terzopoulos, D.: Multilinear Image Analysis for Facial Recognition. In: Proceedings of the International Conference on Pattern Recognition, ICPR 2002 (2002)Google Scholar
  7. 7.
    Alex, M., Vasilescu, O., Terzopoulos, D.: Multilinear Subspace Analysis of Image Ensembles. In: CVPR, vol. II, pp. 93–99 (2003)Google Scholar
  8. 8.
    Alex, M., Vasilescu, O., Terzopoulos, D.: Multilinear Analysis of Image Ensembles: TensorFaces. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 447–460. Springer, Heidelberg (2002)Google Scholar
  9. 9.
    YILMAZ, A., GOKMEN, M.: Eigenhill vs. Eigenface and Eigenedge. Pattern Recognition Journal 34(2001), 181–184 (2000)Google Scholar
  10. 10.
    Kim, H.-C., Kim, D., Bang, S.Y.: FACE RETRIEVAL USING 1ST- AND 2ND-ORDER PCA MIXTURE MODEL. In: Proc. International Conference on Image Processing (ICIP2002), Rochester, USA, September, pp. 605–608 (2002)Google Scholar
  11. 11.
    Lu, J., Plataniotis, K.N., Venetsanopoulos, A.N.: Face Recognition Using Kernel Direct Discriminant Analysis Algorithms. IEEE Transactions on Neural Networks 14(1), 117–126 (2003)CrossRefGoogle Scholar
  12. 12.
    Lu, J., Plataniotis, K.N., Venetsanopoulos, A.N.: Face Recognition Using LDA-Based Algorithms. IEEE Transactions on Neural Networks 14(1), 195–200 (2003)CrossRefGoogle Scholar
  13. 13.
    Wang, X., Qi, H.: Face Recognition Using Optimal Non-orthogonal Wavelet Basis Evaluated By Information Complexity. In: 16 th International Conference on Pattern Recognition (ICPR 2002), August 11 - 15, vol. 1 (2002)Google Scholar
  14. 14.
    Liu, C., Wechsler, H.: Independent Component Analysis of Gabor Features for Face Recognition. IEEE Transactions on Neural Networks 14(4), 919–928 (2003)CrossRefGoogle Scholar
  15. 15.
    Zhao, W., Chellappa, R.: Robust Face Recognition using Symmetric Shape-from-Shading., Center for Automation Research, University of Maryland, College Park, Technical Report CAR-TR-919Google Scholar
  16. 16.
    Belhumeur, P., Kriegman, D.: What Is the Set of Images of an Object under All Possible Illumination Conditions. Int’l J.Computer Vision 28(3), 245–260 (1998)CrossRefGoogle Scholar
  17. 17.
    Nillius, P., Eklundh, J.-O.: Low-Dimensional Representations of Shaded Surfaces under Varying Illumination. In: 2003 Conference on Computer Vision and Pattern Recognition (CVPR 2003), Madison, Wisconsin, June 18 - 20, vol. II, p. 185 (2003)Google Scholar
  18. 18.
    Zhang, L., Samaras, D.: Face Recognition Under Variable Lighting using Harmonic Image Exemplars. In: Proc.CVPR 2003, pp. I: 19-25 (2003)Google Scholar
  19. 19.
    Wang, H., Wang, Y., Wei, H.: Face Representation and Reconstruction under Different Illunimation Conditions. In: Seventh International Conference on Information Visualization (IV 2003), July16 - 18, p. 72 (2003)Google Scholar
  20. 20.
    Basri, R., Jacobs, D.W.: Lambertian Reflectance and Linear Subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(2) (February 2003)Google Scholar
  21. 21.
    Ramamoorthi, R.: Analytic PCA construction for theoretical analysis of lighting variability, including attached shadows, in a single image of a convex Lambertian object. IEEE PAMI 24(10), 1322–1333 (2002)Google Scholar
  22. 22.
    Epstein, R., Hallinan, P., Yuille, A.: 5 plus or minus 2 eigenimages suffice: An empirical investigation of lowdimensional lighting models. In: IEEE Workshop on Physics-Based Modeling in Computer Vision, pp. 108–116 (1995)Google Scholar
  23. 23.
    Hallinan, P.: A low-dimensional representation of human faces for arbitrary lighting conditions. In: CVPR 1994, pp. 995–999 (1994); IJCV 35(3), 203–222 (1999).Google Scholar
  24. 24.
    Qing, L., Shan, S., Gao, W.: Face De-lighting under Natural Illumination. Advances in Biometrics (2), 43 Google Scholar
  25. 25.
    Sim, T., Kanade, T.: Combining Models and Exemplars for Face Recognition: an Illumination Example. In: Proc. Of Workshop on Models versus Exemplars in Computer Vision, CVPR 2001 (2001)Google Scholar
  26. 26.
    Kolda, T.G.: Orthogonal tensor decompositions. SIAM Journal on Matrix Analysis and Applications 23(1), 243–255 (2001)MATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    Qing, L., Shan, S., Gao, W.: Illumination Alignment for Face Image with Ratio Image. Advances in Biometrics (2), 106 Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yuequan Luo
    • 1
  • Guangda Su
    • 1
  1. 1.The State Key Laboratory of Intelligent Technology and System, Electronic Engineering DepartmentTsinghua UniversityBeijingChina

Personalised recommendations