Color Constancy Via Convex Kernel Optimization

  • Xiaotong Yuan
  • Stan Z. Li
  • Ran He
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4843)


This paper introduces a novel convex kernel based method for color constancy computation with explicit illuminant parameter estimation. A simple linear render model is adopted and the illuminants in a new scene that contains some of the color surfaces seen in the training image are sequentially estimated in a global optimization framework. The proposed method is fully data-driven and initialization invariant. Nonlinear color constancy can also be approximately solved in this kernel optimization framework with piecewise linear assumption. Extensive experiments on real-scene images validate the practical performance of our method.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Buchsbaum, G.: A spatial processor model for object color perception. Journal of Franklin Institute 310(1), 1–26 (1980)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Comaniciu, D., Meer, P.: Mean shft: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(5), 603–619 (2002)CrossRefGoogle Scholar
  3. 3.
    Forsyth, D.A.: A novel algorithm for color constancy. International Journal of Computer Vision 5(1), 5–36 (1990)CrossRefGoogle Scholar
  4. 4.
    Gilbert, A., Bowden, R.: Tracking objects across cameras by incremetanlly learning inter-camera colour calibration and patterns of activity. In: European Conference on Computer Vision, vol. 2, pp. 125–136 (2006)Google Scholar
  5. 5.
    Hall, J., McGann, J., Land, E.: Color mondrian experiments: the study of average spectral distributions. J. Opt. Soc. Amer. A(67), 1380 (1977)Google Scholar
  6. 6.
    Finlayson, G., Banard, K., Funt, B.: Color constancy for scenes with varying illumination. Computer Visualization and Image Understanding 65(2), 311–321 (1997)CrossRefGoogle Scholar
  7. 7.
    Li., S.Z.: Robustizing robust m-estimation using deterministic annealing. Pattern Recognition 29(1), 159–166 (1996)CrossRefGoogle Scholar
  8. 8.
    Manduchi, R.: Learning outdoor color classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(11), 1713–1723 (2006)CrossRefGoogle Scholar
  9. 9.
    Marimont, D.H., Wandell, B.A.: Linear models of surface and illuminant spectra. J. Opt. Soc. Amer. 9(11), 1905–1913 (1992)CrossRefGoogle Scholar
  10. 10.
    Rockfellar, R.: Convex Analysis. Princeton Press (1970)Google Scholar
  11. 11.
    Shen, C., Brooks, M.J., Hengel, V.A.: Fast global kernel density mode seeking with application to localization and tracking. In: IEEE International Conference on Computer Vision, vol. 2, pp. 1516–1523. IEEE, Los Alamitos (2005)CrossRefGoogle Scholar
  12. 12.
    Tieu, K., Miller, E.G.: Unsupervised color constancy. In: Thrun, S., Becker, S., Obermayer, K. (eds.) Advances in Neural Information Processing Systems 15, MIT Press, CambridgeGoogle Scholar
  13. 13.
    Tsin, Y., Ramesh, V., Collins, R., Kanade, T.: Bayesian color constancy for outdoor object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 1132–1139 (2001)Google Scholar
  14. 14.
    Funt, B.V., Gardei, V.C., Barnard, K.: Modeling color constancy with neural networks. In: International Conference on Visual Recognition and Action: Neural Models of Mind and Machine (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Xiaotong Yuan
    • 1
  • Stan Z. Li
    • 1
  • Ran He
    • 1
  1. 1.Center for Biometrics and Security Research, Institute of Automation, Chinese Academy of Science, Beijing,100080China

Personalised recommendations