Toward a Full Probability Model of Edges in Natural Images

  • Kim S. Pedersen
  • Ann B. Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2350)


We investigate the statistics of local geometric structures in natural images. Previous studies [13,14] of high-contrast 3×3 natural image patches have shown that, in the state space of these patches, we have a concentration of data points along a low-dimensional non-linear manifold that corresponds to edge structures. In this paper we extend our analysis to a filter-based multiscale image representation, namely the local 3-jet of Gaussian scale-space representations. A new picture of natural image statistics seems to emerge, where primitives (such as edges, blobs, and bars) generate low-dimensional non-linear structures in the state space of image data.


Natural image statistics probability model of local geometry scale-space image features biologically-inspired computational models 


  1. 1.
    G. Arfken. Mathematical Methods for Physicists. Computational Imaging and Vision. Academic Press, London, 1985.Google Scholar
  2. 2.
    A. J. Bell and T. J. Sejnowski. The ”independent components” of natural scenes are edge filters. Vision Research, 37:3327–3338, 1997.CrossRefGoogle Scholar
  3. 3.
    A. Desolneux, L. Moisan, and J. Morel. Partial gestalts. Technical Report CMLA 2001–22, CMLA, Cachan, France, 2001.Google Scholar
  4. 4.
    D. J. Field. Relations between the statistics of natural images and the response proporties of cortical cells. J. Optic. Soc. of Am., 4(12):2379–2394, 1987.CrossRefGoogle Scholar
  5. 5.
    L. Florack. Image Structure. Computational Imaging and Vision. Kluwer Academic Publishers, Dordrecht, 1997.Google Scholar
  6. 6.
    L. Florack, B. ter Haar Romeny, M. Viergever, and J. Koenderink. The gaussian scale-space paradigm and the multiscale local jet. IJCV, 18:61–75, 1996.CrossRefGoogle Scholar
  7. 7.
    J. Huang, A. Lee, and D. Mumford. Statistics of range images. In Proc. of CVPR’00, 2000.Google Scholar
  8. 8.
    J. Huang and D. Mumford. Statistics of natural images and models. In Proc. of CVPR’99, 2000.Google Scholar
  9. 9.
    A. Hyvärinen. Survey on independent component analysis. Neural Computing Surveys, 2:94–128, 1999.Google Scholar
  10. 10.
    J. J. Koenderink. The structure of images. Biol. Cybern., 50:363–370, 1984.zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    J. J. Koenderink and A. J. van Doorn. Representation of local geometry in the visual system. Biol. Cybern., 55:367–375, 1987.zbMATHCrossRefGoogle Scholar
  12. 12.
    J. J. Koenderink and A. J. van Doorn. Metamerism in complete sets of image operators. In K. Bowyer and N. Ahuja, editors, Advances in Image Understanding, pages 113–129. IEEE Comp. Soc. Press, 1996.Google Scholar
  13. 13.
    A. B. Lee, K. S. Pedersen, and D. Mumford. The complex statistics of high-contrast patches in natural images. In WWW Proc. of 2nd Int. IEEE Workshop on Statistical and Computational Theories of Vision, Vancouver, Canada, 2001.
  14. 14.
    A. B. Lee, K. S. Pedersen, and D. Mumford. The nonlinear statistics of high-contrast patches in natural images. Technical Report APPTS Report #01-3, Brown University, USA, 2001.Google Scholar
  15. 15.
    T. Lindeberg. Scale-Space Theory in Computer Vision. Kluwer, 1994.Google Scholar
  16. 16.
    J. Malik, S. Belongie, T. Leung, and J. Shi. Contour and texture analysis for image segmentation. IJCV, 43(1):7–27, 2001.zbMATHCrossRefGoogle Scholar
  17. 17.
    S. Mallat. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transaction on PAMI, 11:674–693, 1989.zbMATHGoogle Scholar
  18. 18.
    D. Marr. Vision. W. H. Freeman, New York, 1982.Google Scholar
  19. 19.
    D. Mumford and B. Gidas. Stochastic models for generic images. Quarterly of Applied Mathematics, 59(11):85–111, March 2001.Google Scholar
  20. 20.
    M. Nielsen and M. Lillholm. What do features tell about images? In Michael Kerckhove, editor, Scale-Space and Morphology in Computer Vision, LNCS 2106, pages 39–50, 2001.CrossRefGoogle Scholar
  21. 21.
    B. A. Olshausen and D. J. Field. Natural image statistics and efficient coding. Network: Computation in Neural Systems, 7(2):333–339, May 1996.Google Scholar
  22. 22.
    D. Ruderman and W. Bialek. Statistics of natural images: Scaling in the woods. Physical Review Letters, 73(6):814–817, August 1994.Google Scholar
  23. 23.
    E. P. Simoncelli. Bayesian denoising of visual images in the wavelet domain. In P. Müller and B Vidakovic, editors, Bayesian Inference in Wavelet Based Models, pages 291–308. Springer-Verlag, New York, 1999.Google Scholar
  24. 24.
    E. P. Simoncelli. Modelling the joint statistics of images in the wavelet domain. In Proc. of SPIE, 44th Annual Meating, volume 3813, pages 188–195, Denver, 1999.CrossRefGoogle Scholar
  25. 25.
    J. H. van Hateren and A. van der Schaaf. Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. R. Soc. Lond. Series B, 265:359–366, 1998.CrossRefGoogle Scholar
  26. 26.
    M. J. Wainwright and E. P. Simoncelli. Scale mixtures of gaussians and the statistics of natural images. In S. A. Solla et al., editor, Advances in Neural Information Processing Systems 12, pages 855–861. MIT Press, 2000.Google Scholar
  27. 27.
    C. Zetzsche, B. Wegmann, and E. Barth. Nonlinear aspects of primary vision: Entropy reduction beyond decorrelation. In Int’l Symposium, Society for Information Display, volume 24, pages 933–936, 1993.Google Scholar
  28. 28.
    S. C. Zhu and D. Mumford. Grade: Gibbs reaction and diffusion equations. — a framework for pattern synthesis, image denoising, and removing clutter. In Proc. of ICCV’98, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Kim S. Pedersen
    • 1
  • Ann B. Lee
    • 2
  1. 1.DIKUUniversity of CopenhagenCopenhagenØDenmark
  2. 2.Division of Applied MathematicsBrown UniversityProvidenceUSA

Personalised recommendations