Advertisement

The Statistical Properties of Local Log-Contrast in Natural Images

  • Jussi T. Lindgren
  • Jarmo Hurri
  • Aapo Hyvärinen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

The study of natural image statistics considers the statistical properties of large collections of images from natural scenes, and has applications in image processing, computer vision, and visual computational neuroscience. In the past, a major focus in the field of natural image statistics have been the statistics of outputs of linear filters. Recently, attention has been turning to nonlinear models. The contribution of this paper is the empirical analysis of the statistical properties of a central nonlinear property of natural scenes: the local log-contrast. To this end, we have studied both second-order and higher-order statistics of local log-contrast. Second-order statistics can be observed from the average amplitude spectrum. To examine higher-order statistics, we applied a higher-order-statistics-based model called independent component analysis to images of local log-contrast. Our results on second-order statistics show that the local log-contrast has a power-law-like average amplitude spectrum, similarly as the original luminance data. As for the higher-order statistics, we show that they can be utilized to learn intuitively meaningful spatial local-contrast patterns, such as contrast edges and bars. In addition to shedding light on the fundamental statistical properties of natural images, our results have important consequences for the analysis and design of multilayer statistical models of natural image data. In particular, our results show that in the case of local log-contrast, oriented and localized second-layer linear operators can be learned from the higher-order statistics of the nonlinearly mapped output of the first layer.

Keywords

Independent Component Analysis Amplitude Spectrum Natural Image Independent Component Analysis Natural Scene 
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.

References

  1. 1.
    Simoncelli, E.P.: Statistical modeling of photographic images. In: Bovik, A. (ed.) Handbook of Image & Video Processing, 2nd edn., pp. 431–441. Academic Press, London (2005)Google Scholar
  2. 2.
    Portilla, J., Strela, V., Wainwright, M.J., Simoncelli, E.P.: Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE Transactions on Image Processing 12(11), 1338–1351 (2003)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Olshausen, B.A., Field, D.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583), 607–609 (1996)CrossRefGoogle Scholar
  4. 4.
    van Hateren, J.H., van der Schaaf, A.: Independent component filters of natural images compared with simple cells in primary visual cortex. Proceedings of the Royal Society of London B 265(1394), 359–366 (1998)CrossRefGoogle Scholar
  5. 5.
    Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, Chichester (2001)Google Scholar
  6. 6.
    Hoyer, P.O., Hyvärinen, A.: A multi-layer sparse coding network learns contour coding from natural images. Vision Research 42(12), 1593–1605 (2002)CrossRefGoogle Scholar
  7. 7.
    Hurri, J.: Learning cue-invariant visual responses. In: Weiss, Y., Schölkopf, B., Platt, J. (eds.) Advances in Neural Information Processing Systems, vol. 18, pp. 539–546. The MIT Press, Cambridge (2006)Google Scholar
  8. 8.
    Landy, M.S., Graham, N.: Visual perception of texture. In: Chalupa, L.M., Werner, J.S. (eds.) The Visual Neurosciences, vol. 2, pp. 1106–1118. The MIT Press, Cambridge (2004)Google Scholar
  9. 9.
    Johnson, A.P.: First- and second-order information in natural images: a filter-based approach to image statistics. Journal of the Optical Society of America A 21(6), 913–925 (2004)CrossRefGoogle Scholar
  10. 10.
    Frazor, R.A., Geisler, W.S.: Local luminance and contrast in natural images. Vision Research 46(10), 1585–1598 (2006)CrossRefGoogle Scholar
  11. 11.
    Regan, M.P.: Half-wave linear rectification of a frequency modulated sinusoid. Applied Mathematics and Computation 79(2-3), 137–162 (1996)CrossRefzbMATHGoogle Scholar
  12. 12.
    Ruderman, D.L.: Origins of scaling in natural images. Vision Research 37, 3358–3398 (1997)CrossRefGoogle Scholar
  13. 13.
    Tadmor, Y., Tolhurst, D.J.: Calculating the contrasts that retinal ganglion cells and LGN neurones encounter in natural scenes. Vision Research 40(22), 3145–3157 (2000)CrossRefGoogle Scholar
  14. 14.
    Bex, P.J., Makous, W.: Spatial frequency, phase, and the contrast of natural images. Journal of the Optical Society of America A 19(6), 1096–1106 (2002)CrossRefGoogle Scholar
  15. 15.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  16. 16.
    Atick, J.J., Redlich, A.N.: What does the retina know about natural scenes? Neural Computation 4(2), 196–210 (1992)CrossRefGoogle Scholar
  17. 17.
    Olshausen, B.A., Field, D.: Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Research 37(23), 3311–3325 (1997)CrossRefGoogle Scholar
  18. 18.
    Schwartz, O., Simoncelli, E.P.: Natural signal statistics and sensory gain control. Nature Neuroscience 4(8), 819–825 (2001)CrossRefGoogle Scholar
  19. 19.
    Tumblin, J., Hodgins, J.K., Guenter, B.K.: Two methods for display of high contrast images. ACM Transactions on Graphics 18(1), 56–94 (1999)CrossRefGoogle Scholar
  20. 20.
    Fiorentini, A., Maffei, L.: Contrast perception and electrophysiological correlates. Journal of Physiology 231(1), 61–69 (1973)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Jussi T. Lindgren
    • 1
  • Jarmo Hurri
    • 1
  • Aapo Hyvärinen
    • 1
  1. 1.Helsinki Insititute for Information Technology, Department of Computer Science, University of Helsinki 

Personalised recommendations