Skip to main content

A novel approach to color normalization using neural network


Color is a powerful descriptor that often simplifies object extraction and identification, and many computer vision systems use color to aid object recognition. However, image colors strongly depend on lighting geometry (direction and intensity of light source) and illuminant color (spectral power distribution). Either small variation in the intensity or the change of scene illumination can dramatically make object color changed. To overcome the lighting dependency problem, a color constancy or normalization algorithm should be used for preprocessing. This paper presents a novel approach to performing color normalization. A nonlinear mapping function is estimated using a neural network. Once the mapping function is found accurately, an image under unknown illumination may be transformed to the image under the predetermined illumination, which will be useful for color image processing. Three groups of experiments were conducted. In our experiments, images are processed by various neural networks and the performance is boosted by using a committee machine, and then the mapping errors are estimated and the results are compared with those of other algorithms. The experimental results demonstrate that the performance of the proposed method is superior to that of other color normalization algorithms.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7


  1. 1.

    Nassau K (1998) Color for science, art and technology. Elsevier, Amsterdam

    Google Scholar 

  2. 2.

    MacDonald LW, Luo MR (2002) Colour image science: exploiting digital media. Wiley, Chichester

    Google Scholar 

  3. 3.

    Finlayson GD, Tian GY (1999) Color normalization for color object recognition. Int J Pattern Recognit Artif Intell 13:1271–1285

    Google Scholar 

  4. 4.

    Jameson D, Hurvich LM (1989) Essay concerning color constancy. Annu Rev Psychol 40:1–22

    Google Scholar 

  5. 5.

    Barnard K, Cardei V, Funt B (2002) A comparison of computational color constancy algorithms - Part I: Methodology and experiments with synthesized data. IEEE Trans Image Process 11:972

    Google Scholar 

  6. 6.

    Barnard K, Martin L, Coath A, Funt B (2002) A comparison of computational color constancy algorithms. Part II: Experiments with image data. IEEE Trans Image Process 11:985

    Google Scholar 

  7. 7.

    Maloney LT, Wandell BA (1986) Color constancy: a method for recovering surface spectral reflectance. J Opt Soc Am A Opt Image Sci Vis 3:29–33

    Google Scholar 

  8. 8.

    Dzmura M (1992) Color constancy: surface color from changing illumination. J Opt Soc Am A Opt Image Sci Vis 9:490–493

    Article  Google Scholar 

  9. 9.

    Tominaga S, Wandell BA (1990) Component estimation of surface spectral reflectance. J Opt Soc Am A Opt Image Sci Vis 7:312–317

    Google Scholar 

  10. 10.

    Craven BJ, Foster DH (1992) An operational approach to color constancy. Vis Res 32:1359–1366

    Google Scholar 

  11. 11.

    Buchsbaum G (1980) A spatial processor model for object color perception. J Frank Inst 310:1–26

    Google Scholar 

  12. 12.

    Land EH (1977) The retinex theory of color vision. Sci Am 237:108–129

    Article  Google Scholar 

  13. 13.

    Forsyth DA (1990) A novel algorithm for color constancy. Int J Comput Vis 5:5–36

    Google Scholar 

  14. 14.

    Barnard K (2000) Improvements to gamut mapping colour constancy algorithms. Comput Vis Eccv 2000 Pt I Proc 1842:390–403

    Google Scholar 

  15. 15.

    Tominaga S, Ebisui S, Wandell BA (2001) Scene illuminant classification: brighter is better. J Opt Soc Am A Opt Image Sci Vis 18:55–64

    Google Scholar 

  16. 16.

    Tominaga S, Wandell BA (2002) Natural scene-illuminant estimation using the sensor correlation. Proc IEEE 90:42–56

    Google Scholar 

  17. 17.

    Brainard DH, Freeman WT (1997) Bayesian color constancy. J Opt Soc Am A Opt Image Sci Vis 14:1393–1411

    Google Scholar 

  18. 18.

    Barnard K, Martin L, Funt B (2000) Color by correlation in a three dimensional color space. Presented at 6th European Conference on Computer Vision, Dublin, Ireland

  19. 19.

    Finlayson GD, Hordley SD, Hubel PM (2001) Color by correlation: a simple, unifying framework for color constancy. IEEE Trans Pattern Anal Mach Intell 23:1209

    Google Scholar 

  20. 20.

    Rosenberg C, Hebert M, Thrun S (2001) Color constancy using KL-divergence. In: Proceedings of the IEEE international conference on computer vision. Vancouver, Canada

  21. 21.

    Geusebroek JM, Van den Boomgaard R, Smeulders AWM, Geerts H (2001) Color invariance. IEEE Trans Pattern Anal Mach Intell 23:1338

    Google Scholar 

  22. 22.

    Sonka M, Hlavac V, Boyle R (1999) Image processing, analysis, and machine vision, 2nd edn. PWS, Pacific Grove

    Google Scholar 

  23. 23.

    Cheng HD, Jiang XH, Sun Y, Wang JL (2001) Color image segmentation: advances and prospects. Pattern Recognit 34:2259–2281

    MATH  Google Scholar 

  24. 24.

    Finlayson GD, Schiele B, Crowley JL (1998) Comprehensive color image normalization. In: Proceedings of the 5th European conference on computer vision 1, Freiburg, Germany

  25. 25.

    Lin ZY, Wang JX, Ma KK (2002) Using eigencolor normalization for illumination-invariant color object recognition. Pattern Recognit 35:2629–2642

    MATH  Google Scholar 

  26. 26.

    Courtney SM, Finkel LH, Buchsbaum G (1995) Network simulations of retinal and cortical contributions to color constancy. Vis Res 35:413–434

    Google Scholar 

  27. 27.

    Funt B, Cardei VC, Barnard K (1997) Neural network color constancy and specularly reflecting surfaces. In: Processing of AIC color 97 II, Kyoto, Japan

  28. 28.

    Cardei VC, Funt B, Barnard K (2002) Estimating the scene illumination chromaticity by using a neural network. J Opt Soc Am A Opt Image Sci Vis 19:2374–2386

    Google Scholar 

  29. 29.

    Agarwal V, Gribok AV, Abidi MA (2007) Machine learning approach to color constancy. Neural Netw 20:559–563

    MATH  Google Scholar 

  30. 30.

    Haykin SS (1999) Neural networks: a comprehensive foundation. 2nd edn.: Institute of Electrical and Electronics Engineers, Prentice-Hall, Upper Saddle River

    MATH  Google Scholar 

  31. 31.

    Funt B, Barnard K, Martin L (1998) Is machine colour constancy good enough? Lect Notes Comput Sci 1406:445

    Google Scholar 

  32. 32.

    Swain MJ, Ballard DH (1991) Color indexing. Int J Comput Vis 7:11–32

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to H. D. Cheng.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Cheng, H.D., Cai, X. & Min, R. A novel approach to color normalization using neural network. Neural Comput & Applic 18, 237–247 (2009).

Download citation


  • Color normalization
  • Color constancy
  • Neural networks
  • Committee machine
  • Genetic algorithm