International Journal of Computer Vision

, Volume 41, Issue 1–2, pp 35–59 | Cite as

Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves Model

  • Ann B. Lee
  • David Mumford
  • Jinggang Huang


We develop a scale-invariant version of Matheron's “dead leaves model” for the statistics of natural images. The model takes occlusions into account and resembles the image formation process by randomly adding independent elementary shapes, such as disks, in layers. We compare the empirical statistics of two large databases of natural images with the statistics of the occlusion model, and find an excellent qualitative, and good quantitative agreement. At this point, this is the only image model which comes close to duplicating the simplest, elementary statistics of natural images—such as, the scale invariance property of marginal distributions of filter responses, the full co-occurrence statistics of two pixels, and the joint statistics of pairs of Haar wavelet responses.

natural images stochastic image model non-Gaussian statistics scaling dead leaves model occlusions clutter 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alvarez, L., Gousseau Y., and Morel J.-M. 1999. The size of objects in natural and artificial images. Advances in Imaging and Electron Physics, vol. 111. Academic Press: San Diego, CA, pp. 167-242.Google Scholar
  2. Buccigrossi, R.W. and Simoncelli, E.P. 1999. Image compression via joint statistical characterization in the wavelet domain. Proc. IEEE Trans. on Image Processing, 8(12):1688-1701.Google Scholar
  3. Field, D.J. 1987. Relations between the statistics of natural images and the response properties of cortical cells.J. Optical Society of America, A4:2379-2394.Google Scholar
  4. Freeman, W.T. and Pasztor, E.C. 1999. Learning low-level vision. In Proc. IEEE Int. Conf. on Computer Vision, Corfu, Greece.Google Scholar
  5. Grenander, U. and Srivastava, A. 2000. Probability models for clutter in natural images, IEEE Trans. PAMI, in press.Google Scholar
  6. Hallinan P.W., Gordon G.G., Yuille, A.L., Giblin, P., and Mumford, D. 1999. Two-and three-dimensional patterns of the face. A.K. Peters Ltd, Natick, MA.Google Scholar
  7. Heeger, D.J. and Bergen, J.R. 1995. Pyramid based texture analysis/ synthesis. In Computer Graphics Proc., pp. 229-238.Google Scholar
  8. Huang, J., Lee, A., and Mumford, D. 2000. Statistics of range images. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Vol. 1, Hilton Head Island, SC, pp. 324-331.Google Scholar
  9. Huang, J. and Mumford, D. 1999. Statistics of natural images and models. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Vol. 1, Fort Collins, CO, pp. 541-547.Google Scholar
  10. Isard, M. and Blake, A. 1998. CONDENSATION-conditional density propagation for visual tracking. Int. J. Computer Vision, 291:5-28.Google Scholar
  11. Kendall, W.S. and ThÔnnes, E. 1998. Perfect Simulation in Stochastic Geometry. Preprint 323, Department of Statistics, University of Warwick, UK.Google Scholar
  12. Kingman, J.F.C. 1993. Poisson Processes. Oxford Studies in Probability. Clarendon Press, Oxford.Google Scholar
  13. Lee, A.B. and Mumford, D. 1999. An occlusion model generating scale-invariant images. In Proc. IEEEWorkshop on Statistical and Computational Theories of Vision, Fort Collins, CO.Google Scholar
  14. Malik, J., Belongie, S., Shi, J., and Leung, T. 1999. Textons, contours and regions: Cue integration in image segmentation. In Proc. IEEE Int. Conf. Computer Vision, Corfu, Greece.Google Scholar
  15. Mallat, S.G. 1989. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. PAMI, 11:674-693.Google Scholar
  16. Matheron, G. 1968. Modèle séquentiel de partition aléatoire. Technical report, CMM, 1968.Google Scholar
  17. Matheron, G. 1975. Random Sets and Integral Geometry. JohnWiley and Sons: New York. Occlusion Models for Natural Images 59Google Scholar
  18. Moulin, P. and Liu, J. 1999. Analysis of multiresolution image denoising schemes using generalized Gaussian and complexity priors. IEEE Trans. on Information Theory, 453:909-919.Google Scholar
  19. Mumford, D. and Gidas, B. 2000. Stochastic models for generic images. Quarterly Journal of Applied Mathematics Volume LIX, Number 1, March 2001, pp. 85-111.Google Scholar
  20. Olshausen, B.A. and Field, D.J. 1996. Natural image statistics and efficient coding. Network, 7:333-339.Google Scholar
  21. Ruderman, D.L. 1994. The statistics of natural images. Network, 5(4):517-548.Google Scholar
  22. Ruderman, D.L. 1997. Origins of scaling in natural images. Vision Research, 37(23):3385-3395.Google Scholar
  23. Ruderman, D.L. and Bialek, W. 1994. Statistics of natural images: scaling in the woods. Physical Review Letters, 73(6):814-817.Google Scholar
  24. Serra, J.P. 1982. Image Analysis and Mathematical Morphology. Academic Press: London.Google Scholar
  25. Simoncelli, E.P. 1999. Modeling the joint statistics of images in the wavelet domain. In Proc. SPIE 44th Annual Meeting, Vol. 3813, Denver, Colorado.Google Scholar
  26. Simoncelli, E.P. and Adelson, E.H. 1996. Noise removal via bayesianwavelet coring. In Third Int'l Conf. on Image Processing, Lausanne, Switzerland, pp. 379-383.Google Scholar
  27. Sullivan, J., Blake, A., Isard, M., and MacCormick, J. 1999. Object localization by Bayesian correlation. In Proc. Int. Conf. Computer Vision, pp. 1068-1075.Google Scholar
  28. van Hateren, J.H. and van der Schaaf, A. 1998. Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. R. Soc. Lond., B265:359-366.Google Scholar
  29. Wainwright, M.J. and Simoncelli, E.P. 2000. Scale mixtures of gaussians and the statistics of natural images. In Advances in Neural Information Processing Systems 12, Solla, Leen, and Müller(Eds.), MIT Press: Cambridge, MA, pp. 885-861.Google Scholar
  30. Zetzsche, B., Wegmann, B., and Barth, E. 1993. Nonlinear aspects of primary vision: Entropy reduction beyond decorrelation. In Int'l Symp. Soc. for Info. Display, Vol. 24, pp. 933-936.Google Scholar
  31. Zhu, S.C. and Guo, C. 2000. Mathematical modeling of clutter: Descriptive vs. generative models. In Proc. of the SPIE AeroSense Conf. on Automatic Target Recognition, Orlando, FL.Google Scholar
  32. Zhu, S.C., Luo, Q., and Zhang, R. 1999. Effective statistical inference by data-driven markov chain Monte-Carlo. Technical Report, Dept. of Computer and Information Sciences, Ohio State University, Columbus, OH.Google Scholar
  33. Zhu, S. and Mumford, D. 1997. Prior learning and Gibbs reactiondiffusion. IEEE Trans PAMI, 19(11):1236-1250.Google Scholar
  34. Zhu, S.C., Wu, Y.N., and Mumford, D. 1998. FRAME: Filters, random field and maximum entropy-towards a unified theory for texture modeling.Int'l J. Computer Vision, 27(2):1-20.Google Scholar

Copyright information

© Kluwer Academic Publishers 2001

Authors and Affiliations

  • Ann B. Lee
    • 1
  • David Mumford
    • 2
  • Jinggang Huang
    • 2
  1. 1.Department of PhysicsBrown UniversityProvidenceUSA
  2. 2.Division of Applied MathematicsBrown UniversityProvidenceUSA

Personalised recommendations