Advertisement

A Comparative Study of ICA Filter Structures Learnt from Natural and Urban Images

  • Ch. Ziegaus⋆
  • E. W. Lang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)

Abstract

The Neural-JADE and various other ICA algorithms are applied to natural and urban image ensembles to learn appropriate filter structures. The latter are shown to be represented quantitatively by Gabor and Haar wavelets in case of natural and urban image stimuli, respectively. A quantitative comparison concerning various filter characteristics demonstrates the influence of various score functions upon the resulting filter structures. Quantitative comparison will be made also with neurophysiological characteristics of these structures.

Keywords

Spatial Frequency Haar Wavelet Gabor Wavelet Filter Structure Order Cumulant 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    C.L. Bajaj, G. Zhuang (1997) An efficient Algorithm and implementation of Haar wavelets, Technical Report Department of Computer Sciences, Purdue University, West Lafayette, USAGoogle Scholar
  2. 2.
    A.J. Bell, T.J. Sejnowski (1995) An information-maximization approach to blind separation and blind deconvolution, Neural Computation, 7:1129–1159CrossRefGoogle Scholar
  3. 3.
    J.-F. Cardoso, A. Souloumiac (1993) Blind beamforming for non-gaussian signals, IEEE Proceedings-Part F, 140(6):362–370Google Scholar
  4. 4.
    J.G. Daugman (1985) Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filters, J.Opt.Soc.A, 2(7):1160–1169Google Scholar
  5. 5.
    R.L. De Valois, D.G. Albrecht, L.G. Thorell (1982a) Spatial frequency selectivity of cells in Macaque visual cortex, Vision Research, 22:545–559CrossRefGoogle Scholar
  6. 6.
    R.L. De Valois, E.W. Yund, N. Hepler (1982b) The orientation and direction selectivity of cells in Macaque visual cortex, Vision Research, 22:531–544CrossRefGoogle Scholar
  7. 7.
    G. Deco, D. Obradovic (1996) An information theoretic approach to neural computing, Springer Verlag, New YorkzbMATHGoogle Scholar
  8. 8.
    M. Girolami, C. Fyfe (1996) Negentropy and kurtosis as projection pursuit indices provide generalized ICA algorithms, NIPS’96, Aspen, Colorado, 249–266Google Scholar
  9. 9.
    M. Habl, Ch. Bauer, Ch. Ziegaus, E.W. Lang (2000) Analyzing brain tumor related EEG signals with ICA algorithms, in H. Malmgren, M. Borga, L. Niklasson, eds., Persepctives in Neural Computing: Artifical Neural Networks in Medicine and Biology,pp. 131–136, Springer-Verlag BerlinGoogle Scholar
  10. 10.
    J. Karhunen, J. Joutsensalo (1994) Representation and separation of signal using nonlinear PCA type learning, Neural Networks, 7:113–127CrossRefGoogle Scholar
  11. 11.
    T.S. Lee (1996) Image Representation Using 2D Gabor Wavelets, IEEE Trans. Pattern Analysis and Machine Intelligence 18:959–971CrossRefGoogle Scholar
  12. 12.
    J.A. Movshon (1979) Two-dimensional spatial frequency tuning of cat striate cortical neurons, Society of Neuroscience (Abstracts), 9th Annual MeetingGoogle Scholar
  13. 13.
    B.A. Olshausen, D.J. Field (1997) Sparse coding with an overcomplete basis set: A strategy employed by V1?, Vision Research, 37Google Scholar
  14. 14.
    A.J. Parker, M.J. Hawken (1988) Two-dimensional spatial structure of receptive fields in monkey striate cortex, J.Opt.Soc.A, 5(4):598–605Google Scholar
  15. 15.
    D.L. Ruderman (1994) The statistics of natural images, Network, 5:517–548zbMATHCrossRefGoogle Scholar
  16. 16.
    J.G. Taylor, S. Coombes (1993) Learning higher order correlations, Neural Networks 6:423–427CrossRefGoogle Scholar
  17. 17.
    Ch. Ziegaus, E.W. Lang (1998) Statistical Invariances in Artificial, Natural and Urban Images, Z.Naturforsch. 53a:1009–1021Google Scholar
  18. 18.
    Ch. Ziegaus, E.W. Lang (1999) Neural Implementation of the JADE-Algorithm, Lecture Notes in Computer Science 1607:487–497Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Ch. Ziegaus⋆
    • 1
  • E. W. Lang
    • 1
  1. 1.Institute of BiophysicsUniversity of RegensburgRegensburgGermany

Personalised recommendations