Illuminant Change Estimation via Minimization of Color Histogram Divergence

  • Michela Lecca
  • Stefano Messelodi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5646)


We present a new method for computing the change of light possibly occurring between two pictures of the same scene. We approximate the illuminant variation with the von Kries diagonal transform and estimate it by minimizing a functional that measures the divergence between the image color histograms. Our approach shows good performances in terms of accuracy of the illuminant change estimation and of robustness to pixel saturation and Gaussian noise. Moreover we illustrate how the method can be applied to solve the problem of illuminant invariant image recognition.


Recognition Rate Image Retrieval Color Histogram Color Quantization Saturated Pixel 
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. 1.
    Athitsos, V., Hadjieleftheriou, M., Kollios, G., Sclaroff, S.: Query-sensitive embeddings. In: Proc. of SIGMOD 2005, pp. 706–717. ACM Press, New York (2005)Google Scholar
  2. 2.
    Barnard, K., Cardei, V., Funt, B.: A comparison of computational color constancy algorithms. ii: Experiments with image data. IEEE Transactions on Image Processing 11(9), 985–996 (2002)CrossRefGoogle Scholar
  3. 3.
    Berens, J., Finlayson, G.: Log-opponent chromaticity coding of colour space. In: 15th IEEE Int. Conf. on Pattern Recognition, pp. 206–211 (2000)Google Scholar
  4. 4.
    Chong, H.Y., Gortler, S.J., Zickler, T.: The von kries hypothesis and a basis for color constancy. In: Proc. of IEEE ICCV (October 2007)Google Scholar
  5. 5.
    Finlayson, C., Hordley, S., Schaefer, G., Tian, G.Y.: Illuminant and device invariance using histogram equalisation. In: IS&T and SID’s 11th Color Imaging Conference, pp. 205–211 (2003)Google Scholar
  6. 6.
    Finlayson, G.D., Drew, M.S., Funt, B.V.: Diagonal transforms suffice for color constancy. In: Proc. of International Conference of Computer Vision (1993)Google Scholar
  7. 7.
    Finlayson, G.D., Drew, M.S., Funt, B.V.: Color constancy: generalized diagonal transforms suffice. J. Optical Society of America 11(11), 3011–3019 (1994)CrossRefGoogle Scholar
  8. 8.
    Funt, B.V., Barnard, K., Martin, L.: Is machine colour constancy good enough? In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 445–459. Springer, Heidelberg (1998)Google Scholar
  9. 9.
    Geusebroek, J.M., Burghouts, G.J., Smeulders, A.W.M.: The Amsterdam library of object images. International Journal of Computer Vision 61(1), 103–112 (2005)CrossRefGoogle Scholar
  10. 10.
    Lecca, M.: Object recognition in color images by the self configuring system MEMORI. International Journal of Signal Processing 3(3), 176–185 (2006)Google Scholar
  11. 11.
    Lecca, M., Messelodi, S.: Estimating illuminant changes in color images by color histogram comparison. Technical Report FBK - irst, TR 2008-04-001 (April 2008)Google Scholar
  12. 12.
    Provenzi, E., De Carli, L., Rizzi, A.: Mathematical definition and analysis of the retinex algorithm. Journal of the Optical Society of America. Optics, Image Science, and Vision 22(12) (2005)Google Scholar
  13. 13.
    Rizzi, A., Gatta, C., Marini, D.: From Retinex to ACE: issues in developing a new algorithm for unsupervised color equalization. Journal of Electronic Imaging 13(1) (2004)Google Scholar
  14. 14.
    Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. International Journal of Computer Vision 66(3), 231–259 (2006)CrossRefGoogle Scholar
  15. 15.
    Schettini, R., Ciocca, G., Zuffi, S.: A survey of methods for colour image indexing and retrieval in image databases. In: Color Imaging Science: Exploiting Digital Media (2001)Google Scholar
  16. 16.
    Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vision 7(1), 11–32 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Michela Lecca
    • 1
  • Stefano Messelodi
    • 1
  1. 1.Fondazione Bruno Kessler, IRST - 38100 PovoTrentoItaly

Personalised recommendations