Advertisement

Bayesian decision versus voting for image retrieval

  • R. Mohr
  • S. Picard
  • C. Schmid
Object Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

Image retrieval from image databases is usually performed by using global image characteristics. However the use of local image information is highly desirable when only part of the image is of interest. An original solution was introduced in [9] using invariant local signal characteristics. This paper extends this contribution by extending the set of invariants considered to allow illumination change. Then it is shown that the invariant distribution is far from uniform and a probabilistic indexing scheme is proposed. Experimental results validate the approch and the different methods are discussed.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    T.O. Binford and T.S. Levitt. Quasi-invariants: Theory and exploitation. In Proceedings of Darpa Image Understanding Workshop, pages 819–829, 1993.Google Scholar
  2. 2.
    J.B. Burns, R.S. Weiss, and E.M. Riseman. The non-existence of general-case view-invariants. In J.L. Mundy and A. Zisserman, editors, Geometric Invariance in Computer Vision, chapter 6, pages 120–131. The MIT Press, Cambridge, MA, USA, 1992.Google Scholar
  3. 3.
    L. Florack. The Syntactical Structure of Scalar Images. PhD thesis, Universiteit Utrecht, November 1993.Google Scholar
  4. 4.
    J.J. Koenderink and A.J. van Doorn. Representation of local geometry in the visual system. Biological Cybernetics, 55:367–375, 1987.CrossRefPubMedGoogle Scholar
  5. 5.
    A. Pentland, R.W. Picard, and S. Sclaroff. Photobook: Content-based manipulation of image databases. International Journal of Computer Vision, 18(3):233–254, 1996.CrossRefGoogle Scholar
  6. 6.
    Romeny. Geometry-Driven Diffusion in Computer Vision. Kluwer Academic Publishers, 1994.Google Scholar
  7. 7.
    B. Schiele and J.L. Crowley. Object recognition using multidimensional receptive field histograms. In Proceedings of the 4th European Conference on Computer Vision, Cambridge, England, pages 610–619, 1996.Google Scholar
  8. 8.
    B. Schiele and J..L. Crowley. Probabilistic object recognition using multidimensional receptive field histogram. In Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, pages 50–54, 1996.Google Scholar
  9. 9.
    C. Schmid and R. Mohr. Combining greyvalue invariants with local constraints for object recognition. In Proceedings of the Conference on Computer Vision and Pattern Recognition, San Francisco, California, USA, June 1996. ftp://ftp.imag.fr/pub/MOVI/publications/Schmid_cvpr96.ps.z.Google Scholar
  10. 10.
    H. Schulz-Mirbach. Constructing invariant features by averaging techniques. In Proceedings of the 12th International Conference on Pattern Recognition, Jerusalem, Israel, pages 387–390, 1994.Google Scholar
  11. 11.
    M.J. Swain and D.H. Ballard. Color indexing. International Journal of Computer Vision, 7(1):11–32, 1991.CrossRefGoogle Scholar
  12. 12.
    M. Turk and A. Pentland. Face recognition using eigenfaces. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Maui, Hawaii, USA, pages 586–591, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • R. Mohr
    • 1
  • S. Picard
    • 1
  • C. Schmid
    • 1
  1. 1.GRAVIR-IMAG & INRIA Rhône-AlpesMontbonnot Saint-MartinFrance

Personalised recommendations