Comparing Intensity Transformations and Their Invariants in the Context of Color Pattern Recognition

  • Florica Mindru
  • Theo Moons
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2353)


In this paper we compare different ways of representing the photometric changes in image intensities caused by changes in illumination and viewpoint, aiming at a balance between goodness-of-fit and low complexity. We derive invariant features based on generalized color moment invariants - that can deal with geometric and photometric changes of a planar pattern - corresponding to the chosen photometric models. The geometric changes correspond to a perspective skew. We compare the photometric models also in terms of the invariants’ discriminative power and classification performance in a pattern recognition system.


Canonical Variable Invariant Feature Model Selection Criterion Color Band Color Constancy 
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.
    K. Barnard, G.D. Finlayson, B.V. Funt, Color Constancy for scenes with varying illumination, Proceedings of the 4th European Conference in Computer Vision, 1996, pp. 3–15.Google Scholar
  2. 2.
    K. Barnard, L. Martin, B. Funt, A. Coath, A data set for color research, accepted for publication in Color Research and Application, 2001.Google Scholar
  3. 3.
    D. Berwick and S. W. Lee, A Chromaticity Space for Specularity, Illumination Color-and Illumination Pose-Invariant 3-D Object Recognition, Proceedings International Conference on Computer Vision, 1998, pp. 165–170.Google Scholar
  4. 4.
    P. E. Debevec, J. Malik, Recovering High Dynamic Range Radiance Maps from Photographs, SIGGRAPH’97, August 1997.Google Scholar
  5. 5.
    Mark.S. Drew, Jie. Wei, Ze-Nian Li,“On Illumination Invariance in Color Object Recognition”, Technical report 1997, School of Computing Science, Simon Fraser University, Vancouver, Canada.Google Scholar
  6. 6.
    G. Finlayson, M.S. Drew and B. Funt, “Color constancy: Generalized diagonal transforms suffice”, Journal of the Optical society of America A, 11(11):3011–3019, 1994.CrossRefGoogle Scholar
  7. 7.
    D. Forsyth, A novel algorithm for color constancy, Int. Journal of Computer Vision, Vol. 5 (1990), pp. 5–36.CrossRefGoogle Scholar
  8. 8.
    G. Finlayson, “Color constancy in diagonal chromaticity space”, Proc. ICCV 1995 pp. 218–223.Google Scholar
  9. 9.
    B. Funt and G. Finlayson, Color constant color indexing, IEEE Trans. PAMI, Vol. 17 (1995), pp. 522–529.CrossRefGoogle Scholar
  10. 10.
    T. Gevers, and A. W. M. Smeulders, A comparative study of several color models for color image invariant retrieval, Proc. Intern. Workshop on Image Database and Multimedia Search, 1996, pp. 17–23.Google Scholar
  11. 11.
    P. Gros Color illumination models for image matching and indexing, Proceedings International Conference on Pattern recognition, 2000, Vol. 3.Google Scholar
  12. 12.
    G. Healey and D. Slater, Global color constancy: recognition of objects by use of illumination invariant properties of color distributions, J. Opt. Soc. Am. A, Vol. 11 (1994), pp. 3003–3010.CrossRefGoogle Scholar
  13. 13.
    R. A. Johnson and D. W. Wichern, Applied multivariate statistical analysis, Prentice-Hall, 1992.Google Scholar
  14. 14.
    Y. Kanazawa and K. Kanatani Stabilizing Image Mosaicing by Model Selection Lecture Notes in Computer Science 2018, 2000, pp. 35–52Google Scholar
  15. 15.
    J. Matas, D. Koubaroulis and J. Kittler, Colour Image Retrieval and Object Recognition Using the Multimodal Neighbourhood Signature, Proceedings of the 6th European Conference in Computer Vision Dublin, Ireland, 2000.Google Scholar
  16. 16.
    F. Mindru, T. Moons and L. Van Gool, Recognizing color patterns irrespective of viewpoint and illumination, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’ 99), Fort Collins (Colorado), June 1999, pp. 368–373.Google Scholar
  17. 17.
    T. Moons, E. Pauwels, L. Van Gool, and A. Oosterlinck, Foundations of semi-differential invariants, International Journal Computer Vision, Vol. 14 (1995), pp. 25–47.CrossRefGoogle Scholar
  18. 18.
    J. L. Mundy, and A. Zisserman A (eds.), Geometric invariance in computer vision, MIT Press, 1992.Google Scholar
  19. 19.
    J. L. Mundy, A. Zisserman, and D. Forsyth (eds.). Applications of invariance in computer vision, LNCS 825, Springer, 1994.Google Scholar
  20. 20.
    S.K. Nayar, R.M. Bolle, Reflectance Based Object Recognition, International Journal of Computer Vision, 17(3):219–240, 1996.CrossRefGoogle Scholar
  21. 21.
    T. Reiss, Recognizing planar objects using invariant image features, LNCS 676, Springer, 1993.zbMATHCrossRefGoogle Scholar
  22. 22.
    D. Slater and G. Healey, The illumination-invariant recognition of 3D objects using local color invariants, IEEE Trans. PAMI, Vol. 18 (1996), pp. 206–210.CrossRefGoogle Scholar
  23. 23.
    D. Slater, G. Healey, What Is the Spectral Dimensionality of Illumination Functions in Outdoor Scenes?, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 1998, pp. 105–110.Google Scholar
  24. 24.
    M. Swain and D. Ballard, Color indexing, Int. Journal of Computer Vision, Vol. 7 (1991), pp. 11–32.CrossRefGoogle Scholar
  25. 25.
    Van Gool L, Moons T, and Ungureanu D. Geometric/photometric invariants for planar intensity patterns, In Proceedings European Conference on Computer Vision. S pringer, 1996, pp. 642–651.Google Scholar
  26. 26.
    P.H.S. Torr, Model Selection for Two View Geometry: A Review submitted to International Journal of Computer Vision, 2001.Google Scholar
  27. 27.
    L. Van Gool, T. Moons, E. Pauwels, A. Oosterlinck, Vision and Lie’s approach to invariance, Image and vision computing, vol. 13, no. 4, pp. 259–277, 1995, Elsevier Science B.V.CrossRefGoogle Scholar
  28. 28.
    L. Wang and G. Healey, Using Zernike Moments for the Illumination and Geometry Invariant Classification of Multispectral Texture”, IEEE Trans. Image Processing, Vol. 7 (1998), pp. 196–203.CrossRefGoogle Scholar
  29. 29.
    Wolff L. On the relative brightness of specular and diffuse reflection, In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, IEEE Press, 1994, pp. 369–376.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Florica Mindru
    • 1
  • Theo Moons
    • 2
  • Luc Van Gool
    • 1
    • 3
  1. 1.ESAT-PSIKatholieke Universiteit LeuvenLeuvenBelgium
  2. 2.Katholieke Universiteit BrusselBrusselBelgium
  3. 3.ETH-BIWISwiss Federal Institute of TechnologyZürichSwitzerland

Personalised recommendations