Machine Vision and Applications

, Volume 21, Issue 5, pp 789–796 | Cite as

Is local colour normalization good enough for local appearance-based classification?

  • Donovan H. ParksEmail author
  • Martin D. Levine
Short Paper


This paper evaluates the effectiveness of colour normalization techniques when they are applied to small image patches as opposed to the entire image. We evaluate five colour normalization techniques using three different local appearance-based classifiers. Our test sets allow us to independently examine the influence of illumination changes due to lighting colour and geometry. We demonstrate that local colour normalization can significantly improve the performance of a local appearance-based classifier. However, we observe that the effectiveness of local colour normalization depends on both the underlying classifier and the type of illumination variation.


Colour normalization Colour constancy Object recognition Local appearance-based classifier Coherency filtering 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Funt, B., Barnard, K., Martin, L.: Is colour constancy good enough? In: 5th European Conference of Computer Vision, Freiburg, Germany, pp. 445–459 (1998)Google Scholar
  2. 2.
    Obdrž álek, Š., Matas, J., Chum, O.: On the interaction between object recognition and colour constancy. In: IEEE International Workshop on Color and Photometric Methods in Computer Vision, Los Alamitos, USA (2003)Google Scholar
  3. 3.
    Lowe D.: Distinct image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  4. 4.
    Rothganger F., Lazebnik S., Schmid C., Ponce J.: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vis. 63(1), 65–83 (2005)CrossRefGoogle Scholar
  5. 5.
    Obdrzálek, Š., Matas, J.: Object recognition using local affine frames on distinguished regions. In: The Challenge of Image and Video Retrieval (CIVR2002), July (2002)Google Scholar
  6. 6.
    Maree R., Geurts P., Piater J., Wehenkel L.: Random subwindows for robust image classification. Comput. Vis. Pattern Recognit. 1, 34–40 (2005)Google Scholar
  7. 7.
    Finlayson, G.D., Schiele, B., Crowley, J.L.: Comprehensive colour image normalization. In: Fifth European Conference on Computer Vision, pp. 475–490 (1998)Google Scholar
  8. 8.
    Finlayson G.D., Drew M.S., Funt B.V.: Color constancy: generalized diagonal transforms suffice. J. Opt. Soc. Am. A 11, 3011–3020 (1994)CrossRefGoogle Scholar
  9. 9.
    Finlayson g.D., Drew M.S., Funt B.V.: Spectral sharpening: sensor transformations for improved color constancy. J. Opt. Soc. Am. A 11, 1553–1563 (1994)CrossRefGoogle Scholar
  10. 10.
    Finlayson G.D., Funt B.V.: Coefficient channels: derivation and relationship to other theoretical studies. Color Res. Appl. 21, 87–96 (1996)CrossRefGoogle Scholar
  11. 11.
    Funt B.V., Finlayson G.D.: Color constant color indexing. IEEE Trans. Pattern Anal. Mach. Intell. 17, 522–529 (1995)CrossRefGoogle Scholar
  12. 12.
    Gevers T., Smeulders A.: Color-based object recognition. Pattern Recognit. 32, 453–464 (1999)CrossRefGoogle Scholar
  13. 13.
    Swain M.J., Ballard D.H.: Color indexing. Int. J. Comput. Vis. 7, 11–32 (1991)CrossRefGoogle Scholar
  14. 14.
    Chang, P., Krumm, J.: Object recognition with color cooccurrence histograms. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’99), Fort Collins, CO, USA, pp. 2498 (1999)Google Scholar
  15. 15.
    Linde, O., Lindeberg, T.: Object recognition using composed receptive field histograms of higher dimensionality. In: 17th International Conference on Pattern Recognition (ICPR 2004), Cambridge, UK, pp. 1–6 (2004)Google Scholar
  16. 16.
    Ekvall, S., Kragic, D.: Receptive field cooccurrence histograms for object detection. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, Edmonton, Canada (2005)Google Scholar
  17. 17.
    Turk M., Pentland S.: Eigenfaces for recognition. J. Cogn. Neurosci. 3, 71–86 (1991)CrossRefGoogle Scholar
  18. 18.
    Murase H., Nayar S.K.: Visual learning and recognition of 3-D objects from appearance. Int. J. Comput. Vis. 14, 5–24 (1995)CrossRefGoogle Scholar
  19. 19.
    Ohba K., Ikeuchi K.: Detectability, uniqueness, and reliability of eigen-windows for robust recognition of partially occluded objects. IEEE Pattern Anal. Mach. Intell. 19, 1043–1048 (1997)CrossRefGoogle Scholar
  20. 20.
    Parks, D.H.: Object detection and analysis using coherency filtering. In: Department of Electrical and Computer Engineering. M. Eng. McGill University, Montreal ( (2006)
  21. 21.
    Geusebroek J.M., Burghouts G.J., Smeulders A.W.M.: The Amsterdam library of object images. Int. J. Comput. Vis. 61, 103–112 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.Faculty of Computer ScienceDalhousie UniversityHalifaxCanada
  2. 2.Centre for Machine IntelligenceMcGill UniversityMontrealCanada

Personalised recommendations