Skip to main content
SpringerLink
Log in

Feature Coding with a Statistically Independent Cortical Representation

  • Conference paper
  • First Online:
Scale Space Methods in Computer Vision (Scale-Space 2003)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2695))

Included in the following conference series:

  • 1003 Accesses

Abstract

Current models of primary visual cortex (V1) include a linear filtering stage followed by a gain control mechanism that explains some of the nonlinear behavior of neurons. The nonlinear stage has been modeled as a divisive normalization in which each input linear response is squared and then divided by a weighted sum of squared linear responses in a certain neighborhood. In this communication, we show that such a scheme permits an efficient coding of natural image features. In our case, the linear stage is implemented as a four-level Daubechies decomposition, and the nonlinear normalization parameters are determined from the statistics of natural images under the hypothesis that sensory systems are adapted to signals to which they are exposed. In particular, we fix the weights of the divisive normalization to the mutual information of the corresponding pair of linear coefficients. This nonlinear process extracts significant, statistically independent, visual events in the image.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • 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

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. D. Hubel, and T. Wiesel, “Receptive fields, binocular interaction, and functional architecture in the cat’s visual cortex”, J. Physiol (Lond), 160, pp. 106–154, 1962.

    Google Scholar 

  2. J. A. Movshon, I. D. Thompson, and D. J. Tholhurst, “Spatial summation in the receptive fields of simple cells in the cat’s striate cortex”, J. Physiol (Lond), 283, pp. 53–77, 1978.

    Google Scholar 

  3. A. B. Bonds, “Role of inhibition in the specification of orientation selectivity of cells in the cat striate cortex”, Visual Neuroscience, 2, pp. 41–55, 1989.

    Article  Google Scholar 

  4. W. S. Geisler, and D. G. Albrecht, “Cortical neurons: Isolation of contrast gain control”, Vision Research, 8, pp. 1409–1410, 1992.

    Article  Google Scholar 

  5. D. J. Heeger, “Normalization of cell responses in cat striate cortex”, Visual Neuroscience, 9, pp. 181–198, 1992.

    Google Scholar 

  6. M. Carandini, D. J. Heeger, and J. A. Movshon, “Linearity and normalization in simple cells of the macaque primary visual cortex”, J. Neuroscience, 17, pp. 8621–8644, 1997.

    Google Scholar 

  7. F. Attneave, “Some informational aspects of visual perception”, Psych. Rev, 61, pp. 183–193, 1954.

    Article  Google Scholar 

  8. H. B. Barlow, “Possible principles underlying the transformation of sensory messages”, Sensory Communication, p. 217, MIT Press, 1961.

    Google Scholar 

  9. S. B. Laughlin, “A simple coding procedure enhances a neuron’s information capacity”, Z. Naturforsch, 36C, pp. 910–912, 1981.

    Google Scholar 

  10. J. J. Atick, “Could information theory provide an ecological theory of sensory processing?”, Netw. Comput. Neural Syst., 3, pp. 213–251, 1992.

    Article  MATH  Google Scholar 

  11. J. H. van Hateren, “A theory of maximizing sensory information”, Biol. Cybern., 68, pp. 23–29, 1992.

    Article  MATH  Google Scholar 

  12. D. J. Field, “What is the goal of sensory coding?”, Neural Comput., 6, pp. 559–601, 1994.

    Article  Google Scholar 

  13. F. Rieke, D. A. Bodnar, and W. Bialek, “Naturalistic stimuli increase the rate and efficiency of information transmission by primary auditory afferents”, Proc. R. Soc. London B, 262, pp. 259–265, 1995.

    Article  Google Scholar 

  14. E. P. Simoncelli, and O. Schwartz, “Modeling Surround Suppression in V1 Neurons with a Statistically-Derived Normalization Model”, Advances in Neural Information Processing Systems, 11, pp. 153–159, 1999.

    Google Scholar 

  15. M. J. Wainwright, O. Schwartz, and E. P. Simoncelli, “Natural image statistics and divisive normalization: modeling nonlinearities and adaptation in cortical neurons”, Statistical Theories of the Brain, eds. R. Rao, B. Olshausen, and M. Lewicki, MIT Press, 2001.

    Google Scholar 

  16. O. Schwartz, and E. P. Simoncelli “Natural signal statistics and sensory gain control”, Nature neuroscience, 4(8), pp. 819–825, 2001.

    Article  Google Scholar 

  17. B. Wegmann, and C. Zetzsche, “Statistical dependence between orientation filter outputs used in an human vision based image code”. Proc. SPIE Vis. Commun. Image Processing, pp. 1360, 909–922, Soc. Photo-Opt. Instrum. Eng, Lausanne, Switzerland, 1990.

    Google Scholar 

  18. E. P. Simoncelli, “Statistical Models for Images: Compression, Restoration and Synthesis”, Asilomar Conf. Signals, Systems, Comput., pp. 673–679, IEEE Comput. Soc, Los Alamitos, CA, 1997.

    Google Scholar 

  19. P. O. Hoyer, and A. Hyvärinen, “A multi-layer sparse coding network learns contour coding from natural images”, Vision Research, 42(12), pp. 1593–1605, 2002.

    Article  Google Scholar 

  20. I. Daubechies, Ten Lectures on Wavelets, CBMS-NSF Lecture Notes nr. 61, SIAM, 1992.

    Google Scholar 

  21. D. J. Field, “Relations between the statistics of natural images and the response properties of cortical cells”, J. Opt. Soc. Am. A, 4(12), pp. 2379–2394, 1987.

    Google Scholar 

  22. S. G. Mallat, “A theory for multiresolution signal decomposition: The wavelet representation”, IEEE Pat. Anal. Mach. Intell., 11, pp. 674–693, 1989.

    Article  MATH  Google Scholar 

  23. O. Nestares, R. Navarro, J. Portilla, and A. Tabernero, “Efficient Spatial-Domain Implementation of a Multiscale Image Representation Based on Gabor Functions”, Journal of Electronic Imaging, 7(1), pp. 166–173, 1998.

    Article  Google Scholar 

  24. R. W. Buccigrossi, and E. P. Simoncelli, “Image compression via joint statistical characterization in the wavelet domain” IEEE Transactions on Image Processing, 8(12), pp. 1688–1701, 1999.

    Article  Google Scholar 

  25. M. J. Wainwright, and E. P. Simoncelli, “Scale Mixtures of Gaussians and the Statistics of Natural Images”, Advances in Neural Information Processing Systems, 12, pp. 855–861, 2000.

    Google Scholar 

  26. M. J. Wainwright, E. P. Simoncelli, and A. S. Willsky, “Random Cascades on Wavelet Trees and Their Use in Modeling and Analyzing Natural Imagery”, Applied and Computational Harmonic Analysis, 11(1), pp. 89–123.

    Google Scholar 

  27. B. A. Olshausen, and D. J. Field, “Sparse coding with an overcomplete basis set: A strategy employed by V1?”, Vision Research, 37, pp. 3311–3325, 1997.

    Article  Google Scholar 

  28. B. A. Olshausen, “Sparse Codes and Spikes”, Statistical Theories of the Brain, eds. R. Rao, B. Olshausen, and M. Lewicki, pp. 257–272, MIT Press, 2002.

    Google Scholar 

  29. S. Kullback, and R. A. Leibler, “On information and sufficiency”, The Annals of Mathematical Statistics, 22, pp. 79–86, 1951.

    Article  MathSciNet  MATH  Google Scholar 

  30. A. Papoulis, Probability, random variables and stochastic processes (3rd ed.), McGraw-Hill, Inc, Singapore, 1991.

    Google Scholar 

  31. J. Malo, F. Ferri, R. Navarro, and R. Valerio, “Perceptually and Statistically Decorrelated Features for Image Representation: Application to Transform Coding”. Proceedings of the 15 TH International Conference on Pattern Recognition, 3, pp. 242–245, IEEE Computer Society, Barcelona, Spain, 2000.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Instituto de Óptica “Daza de Valdés”, CSIC, Madrid, Spain, 28006

    Roberto Valerio & Rafael Navarro

  2. Faculteit Biomedische Technologie, Technische Universiteit Eindhoven, Eindhoven, The Netherlands, 5600 MB

    Bart M. ter Haar Romeny & Luc Florack

Authors
  1. Roberto Valerio
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rafael Navarro
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bart M. ter Haar Romeny
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Luc Florack
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Imaging Sciences, 5th Floor Thomas Guy House, Guy’s Campus, London, SE1 9RT, UK

    Lewis D. Griffin

  2. IT University of Copenhagen, Glentevej 67-69, Copenhagen NV, Denmark

    Martin Lillholm

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Valerio, R., Navarro, R., ter Haar Romeny, B.M., Florack, L. (2003). Feature Coding with a Statistically Independent Cortical Representation. In: Griffin, L.D., Lillholm, M. (eds) Scale Space Methods in Computer Vision. Scale-Space 2003. Lecture Notes in Computer Science, vol 2695. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44935-3_4

Download citation

  • DOI: https://doi.org/10.1007/3-540-44935-3_4

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40368-5

  • Online ISBN: 978-3-540-44935-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation