Advertisement

Spectro-Spatial Gradients for Color-Based Object Recognition and Indexing

  • Daniel Berwick
  • Sang Wook Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)

Abstract

This paper presents illumination pose- and illumination colorinvariant color feature descriptors for object recognition and indexing which are derived from spectral (color) and spatial derivatives of logarithmic image irradiance. While the use of spatial gradients and spatial ratios of image irradiance have been suggested for limited viewing-pose invariance and illumination-color invariance, respectively, gradients in the spectral direction and combination of spectral and spatial gradients have not been fully investigated. We present a unified framework for analyzing spatial and spectral gradients of logarithmic image irradiance, and suggest that spectro-spatial gradients have rich potential for developing local and global descriptors of object color. Experimental results are presented to demonstrate the efficacy of the proposed descriptors.

Keywords

Feature Vector Object Recognition Database Image Spatial Gradient Illumination Condition 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. Berwick and S. W. Lee. Specualrity-, illumination color-and pose-invariant chromaticity space for 3-d object recognition. In ICCV, pages 165–170, Bombay, India, January, 1998.Google Scholar
  2. 2.
    M.S. Drew, J. Wei, and Z. Li. Illumination invariant color object recognition via compressed chromaticity histograms of color-channel-normalize images. In ICCV, pages 533–540, Bombay, India, January, 1998.Google Scholar
  3. 3.
    G. D. Finlayson. Color in perspective. PAMI, 18(10):1034–1038, 1996.Google Scholar
  4. 4.
    G. D. Finlayson, M. S. Drew, and B. V. Funt. Color constancy: Generalized diagonal transforms suffice. JOSA, 11(11):3011–3019, 1994.Google Scholar
  5. 5.
    G.D. Finlayson, B. Schiele, and J.L. Crowley. Comprehensive colour image normalization. In ECCV, Freiburg, Germany, June, 1998.Google Scholar
  6. 6.
    M. Flickner et al. Query by image and video content: The qbic system. IEEE Computer, 28:23–32, 1991.Google Scholar
  7. 7.
    D. A. Forsyth. A novel approach to colour constancy. IJCV, 5(1):5–36, 1990.CrossRefGoogle Scholar
  8. 8.
    B. V. Funt and G. D. Finlayson. Color constant color indexing. PAMI, 17(5):522–529, 1995.Google Scholar
  9. 9.
    G.H. Healey and D. Slater. Global color constancy: Recognition of objects by use of illumination-invariant properties of color distributions. JOSA, 11(11), 1994.Google Scholar
  10. 10.
    J.J. Koenderink and A.J. van Doorn. Representation of local geometry in the visual system. Biological Cybernetics, 55:367–375, 1987.zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    E.H. Land and J. J. McCann. Lightness and retinex theory. JOSA, 61:1–11, 1971.Google Scholar
  12. 12.
    S. Lin and S.W. Lee. Using chromaticity distributions and eigenspace for pose-, illumination-, and specularity-invariant 3d object recognition. In CVPR, pages 426–431, Puerto Rico, 1997.Google Scholar
  13. 13.
    L. T. Maloney and B. A. Wandell. A computational model of color constancy. JOSA, 1:29–33, 1986.Google Scholar
  14. 14.
    H. Murase and S.K. Nayar. Visual learning and recognition of 3-d objects from appearance. IJCV, 14, 1995.Google Scholar
  15. 15.
    S.K. Nayar and R.M. Bolle. Reflectance based object recognition. IJCV, 17, 1996.Google Scholar
  16. 16.
    C. Schmid and R. Mohr. Local greyvalue invariants for image retrieval. PAMI, 19(5):830–835, 1997.Google Scholar
  17. 17.
    D. Slater and G.H. Healey. The illumination-invariant recognition of 3d objects using local color invariants. PAMI, 18(2), 1996.Google Scholar
  18. 18.
    M.J. Swain and D.H. Ballard. Color indexing. IJCV, 7(1):11–32, 1991.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Daniel Berwick
    • 1
  • Sang Wook Lee
    • 1
  1. 1.University of MichiganAnn ArborUSA

Personalised recommendations