A Statistical Approach for Learning Invariants: Application to Image Color Correction and Learning Invariants to Illumination

  • B. Bascle
  • O. Bernier
  • V. Lemaire
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


This paper presents a new approach for automatic image color correction, based on statistical learning. The method both parameterizes color independently of illumination and corrects color for changes of illumination. The motivation for using a learning approach is to deal with changes of lighting typical of indoor environments such as home and office. The method is based on learning color invariants using a modified multi-layer perceptron (MLP). The MLP is odd-layered. The middle layer includes two neurons which estimate two color invariants and one input neuron which takes in the luminance desired in output of the MLP. The advantage of the modified MLP over a classical MLP is better performance and the estimation of invariants to illumination. The trained modified MLP can be applied using look-up tables (LUTs), yielding very fast processing. Results illustrate the approach.


Illumination Change Corrected Image Color Constancy Color Correction Color Transfer 
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.
    Funt, B., Cardei, V., Barnard, K.: Neural network colour constancy and specularly reflecting surfaces. In: Proc. of AIC Color 1997, Kyoto, Japan (1997)Google Scholar
  2. 2.
    Gevers, T., Smeulders, A.: Color based object recognition. Pattern Recognition (1999)Google Scholar
  3. 3.
    Gonzalez, R., Woods, R.: Digital Image Processing. Addison-Wesley Longman Publishing Co., Inc., Amsterdam (2001)Google Scholar
  4. 4.
    Reinhard, E., Ashikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Computer Graphics and Applications (2001)Google Scholar
  5. 5.
    Finlayson, G., Drew, M., Lu, C.: Intrinsic images by entropy minimization. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 582–595. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Funt, B., Jiang, H.: Non-diagonal colour correction. In: Proc. International Conference on Image Processing (ICIP 2003), Barcelona (2003)Google Scholar
  7. 7.
    Tao, L., Asari, V.: Modified luminance based msr for fast and efficient image enhancement. In: Proc. of 32nd Applied Imagery Pattern Recognition Workshop (AIPR 2003) (2003)Google Scholar
  8. 8.
    Yin, J., Cooperstock, J.: Color correction methods with applications to digital projection environments. Journal of the Winter School of Computer Graphics (2004)Google Scholar
  9. 9.
    Barnard, K., Martin, L., Coath, A., Funt, B.: A comparison of computational color constancy algorithms, part 2, experiments with images. IEEE Transactions on Image Processing (2002)Google Scholar
  10. 10.
    Land, E., McCann, J.: Lightness and retinex theory. J. Opt. Soc. Am. (1971)Google Scholar
  11. 11.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1996)MATHGoogle Scholar
  12. 12.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proc. of IEEE Conf. on Comp. Vis. and Pat. Rec (CVPR 2000) (2000)Google Scholar
  13. 13.
    Tappen, M., Freeman, W., Adelson, E.: Recovering intrinsic images from a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence (2005)Google Scholar
  14. 14.
    Luo, Q., Khoshgoftaar, T.: Efficient image segmentation by mean shift clustering and MDL-guided region merging. In: Proc. of 16th IEEE Int. Conf. on Tools with Artificial Intelligence (ICTAI 2004) (2004)Google Scholar
  15. 15.
    Gu, I.H., Gui, V.: Colour image segmentation using adaptive mean shift filters. In: Proc. of Int. Conference on Image Processing (ICIP 2001) (2001)Google Scholar
  16. 16.
    Tominaga, S.: Color coordinate conversion via neural networks. In: Proc. of International Conf. on Colour Imaging in Multimedia (CIM 1998) (1998)Google Scholar
  17. 17.
    Vrhel, M., Trussell, H.: Color scanner calibration via a neural network. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 1999) (1999)Google Scholar
  18. 18.
    Rosenberg, C., Minka, T., Ladsariya, A.: Bayesian color constancy with non-gaussian models (NIPS 2003) (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • B. Bascle
    • 1
  • O. Bernier
    • 1
  • V. Lemaire
    • 1
  1. 1.Orange / France Telecom R & D 

Personalised recommendations