Skip to main content

How Well Do Filter-Based MRFs Model Natural Images?

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNIP,volume 7476)

Abstract

Markov random fields (MRFs) have found widespread use as models of natural image and scene statistics. Despite progress in modeling image properties beyond gradient statistics with high-order cliques, and learning image models from example data, existing MRFs only exhibit a limited ability of actually capturing natural image statistics. In this paper we investigate this limitation of previous filter-based MRF models, which appears in contradiction to their maximum entropy interpretation. We argue that this is due to inadequacies in the leaning procedure and suggest various modifications to address them. We demonstrate that the proposed learning scheme allows training more suitable potential functions, whose shape approaches that of a Dirac-delta function, as well as models with larger and more filters. Our experiments not only indicate a substantial improvement of the models’ ability to capture relevant statistical properties of natural images, but also demonstrate a significant performance increase in a denoising application to levels previously unattained by generative approaches.

Keywords

  • Natural Image
  • Image Denoising
  • Contrastive Divergence
  • Restricted Boltzmann Machine
  • Boundary Pixel

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.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (Canada)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE T. Image Process. 16(8), 2080–2095 (2007)

    CrossRef  MathSciNet  Google Scholar 

  2. Geman, D., Reynolds, G.: Constrained restoration and the recovery of discontinuities. IEEE T. Pattern Anal. Mach. Intell. 14(3), 367–383 (1992)

    CrossRef  Google Scholar 

  3. Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)

    CrossRef  MATH  Google Scholar 

  4. Huang, J.: Statistics of Natural Images and Models. Ph.D. thesis, Brown University (2000)

    Google Scholar 

  5. Köster, U., Lindgren, J.T., Hyvärinen, A.: Estimating Markov Random Field Potentials for Natural Images. In: Adali, T., Jutten, C., Romano, J.M.T., Barros, A.K. (eds.) ICA 2009. LNCS, vol. 5441, pp. 515–522. Springer, Heidelberg (2009)

    CrossRef  Google Scholar 

  6. Levin, A., Nadler, B.: Natural image denoising: Optimality and inherent bounds. In: CVPR 2011 (2011)

    Google Scholar 

  7. Lyu, S., Simoncelli, E.P.: Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures. IEEE T. Pattern Anal. Mach. Intell. 31(4), 693–706 (2009)

    CrossRef  Google Scholar 

  8. Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Non-local sparse models for image restoration. In: ICCV 2009 (2009)

    Google Scholar 

  9. McAuley, J.J., Caetano, T., Smola, A.J., Franz, M.O.: Learning high-order MRF priors of color images. In: ICML 2006, pp. 617–624 (2006)

    Google Scholar 

  10. Norouzi, M., Ranjbar, M., Mori, G.: Stacks of convolutional restricted Boltzmann machines for shift-invariant feature learning. In: CVPR 2009 (2009)

    Google Scholar 

  11. Portilla, J., Strela, V., Wainwright, M.J., Simoncelli, E.P.: Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE T. Image Process. 12(11), 1338–1351 (2003)

    CrossRef  MathSciNet  Google Scholar 

  12. Ranzato, M., Mnih, V., Hinton, G.E.: Generating more realistic images using gated MRF’s. In: NIPS 2010 (2010)

    Google Scholar 

  13. Roth, S., Black, M.J.: On the spatial statistics of optical flow. Int. J. Comput. Vision 74(1), 33–50 (2007)

    CrossRef  Google Scholar 

  14. Roth, S., Black, M.J.: Fields of experts. Int. J. Comput. Vision 82(2), 205–229 (2009)

    CrossRef  Google Scholar 

  15. Ruderman, D.L.: The statistics of natural images. Network: Comp. Neural 5(4), 517–548 (1994)

    CrossRef  MATH  Google Scholar 

  16. Schmidt, U., Gao, Q., Roth, S.: A generative perspective on MRFs in low-level vision. In: CVPR 2010 (2010)

    Google Scholar 

  17. Tieleman, T.: Training restricted boltzmann machines using approximations to the likelihood gradient. In: ICML 2008 (2008)

    Google Scholar 

  18. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE T. Image Process. 13(4), 600–612 (2004)

    CrossRef  Google Scholar 

  19. Weiss, Y., Freeman, W.T.: What makes a good model of natural images? In: CVPR 2007 (2007)

    Google Scholar 

  20. Welling, M., Hinton, G.E., Osindero, S.: Learning sparse topographic representations with products of Student-t distributions. In: NIPS 2002, pp. 1359–1366 (2002)

    Google Scholar 

  21. Zhu, S.C., Mumford, D.: Prior learning and Gibbs reaction-diffusion. IEEE T. Pattern Anal. Mach. Intell. 19(11), 1236–1250 (1997)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Gao, Q., Roth, S. (2012). How Well Do Filter-Based MRFs Model Natural Images?. In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds) Pattern Recognition. DAGM/OAGM 2012. Lecture Notes in Computer Science, vol 7476. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32717-9_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-32717-9_7

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-32716-2

  • Online ISBN: 978-3-642-32717-9

  • eBook Packages: Computer ScienceComputer Science (R0)