Robust ICA Neural Network and Application on Synthetic Aperture Radar (SAR) Image Analysis

  • Jian Ji
  • Zheng Tian
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


Independent component analysis (ICA) has shown success in the separation of sources in lots of applications. However, in synthenic aperture radar (SAR) images the noise is multiplicative, so the applicability of ICA is seriously reduced. This paper proposes a new robust independent component analysis neural network (RICANN) that improves the robustness of ICA by adding outlier rejection rule. Its application in synthetic aperture radar (SAR) is discussed. The results show the potential usage in SAR image processing problems.


Independent Component Analysis Synthenic Aperture Radar Independent Component Analysis Synthenic Aperture Radar Image Blind Source Separation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bell, A.J., Sejnowski, T.J.: An information maximization approach to blind separation and blind deconvolution. Neural Computation 7, 1129–1159 (1999)CrossRefGoogle Scholar
  2. 2.
    Lee, T., Lewicki, M., Sejnowski, T.: Independent component analysis using an ex-tended infomax algorithm for mixed sub-gaussian and super-gaussian sources. Neural Computation 11, 409–433 (1999)CrossRefGoogle Scholar
  3. 3.
    Cardoso, J.-F.: High-order contrasts for independent component analysis. Neural Computation 11, 157–192 (1999)CrossRefGoogle Scholar
  4. 4.
    Amari, S., Cichocki, A.: Adaptive blind signal processing - neural network approaches. Proc. IEEE 86, 2026–2048 (1998)CrossRefGoogle Scholar
  5. 5.
    Cruces, S., Castedo, L., Cichocki, A.: Robust blind source separation algorithms using cumulants. Neurocomputing 49, 87–118 (2002)MATHCrossRefGoogle Scholar
  6. 6.
    Hyvarinen, A.: Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Trans. NN 10, 626–634 (1999)Google Scholar
  7. 7.
    Hyvarinen, A.: Gaussian moments for noisy independent component analysis. IEEE Signal Processing Letters 6, 145–147 (1999)CrossRefGoogle Scholar
  8. 8.
    Attias, H.: Independent Factor Analysis. Neural Computation 11, 803–851 (1999)CrossRefGoogle Scholar
  9. 9.
    Moulines, E., Cardoso, J.F., Gassiat, E.: Maximum likelihood for blind separation and de-convolution of noisy signals using mixture models. In: Proc. ICASSP 1997, vol. 5, pp. 3617–3620 (1997)Google Scholar
  10. 10.
    Pandey, S., Billor, N., Turkmen, A.: The effect of outliers in independent component analysis. In: Twelfth Annual International Conference on Statistics, Combinatorics, Mathematics and Applications (December 2005)Google Scholar
  11. 11.
    Hubert, M., Rousseeuw, P.J., Vanden Branden, K.: ROBPCA: a new approach to robust principal component analysis. Technometrics (47), 64–79 (2005)Google Scholar
  12. 12.
    Rousseeuw, P.J., Van Driessen, K.: A Fast Algorithm for the Minimum Covariance Determinant Estimator. Technometrics (41), 212–223 (1999)Google Scholar
  13. 13.
    Adams, J.B., Smith, M.O., Johnson, P.E.: Spectral mixture modeling-A new analysis of rock and soil types at the Viking Lander 1 site. J. Geophys. Res. 91(B8), 8090–8112 (1986)CrossRefGoogle Scholar
  14. 14.
    Cichocki, A., Amari, S.: Adaptive Blind Signal and Image Processing. John Wiley and Sons, Chichester (2002)CrossRefGoogle Scholar
  15. 15.
    Giannakopoulos, X., Karhunen, J., Oja, E.: An experimental comparison of neural algo-rithms for independent component analysis and blind separation. International Journal of Neural Systems 9(2), 99–114 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jian Ji
    • 1
  • Zheng Tian
    • 2
    • 3
  1. 1.Department of Computer Science & TechnologyNorthwestern Polytechnical UniversityXi’anChina
  2. 2.Department of Applied MathematicsNorthwestern Polytechnical UniversityXi’anChina
  3. 3.Key Laboratory of Education Ministry for Image Processing and Intelligent ControlHuazhong University of Science & TechnologyWuhanChina

Personalised recommendations