Skip to main content

Robust Sparse Component Analysis Based on a Generalized Hough Transform

Abstract

An algorithm called Hough SCA is presented for recovering the matrix in, where is a multivariate observed signal, possibly is of lower dimension than the unknown sources. They are assumed to be sparse in the sense that at every time instant, has fewer nonzero elements than the dimension of. The presented algorithm performs a global search for hyperplane clusters within the mixture space by gathering possible hyperplane parameters within a Hough accumulator tensor. This renders the algorithm immune to the many local minima typically exhibited by the corresponding cost function. In contrast to previous approaches, Hough SCA is linear in the sample number and independent of the source dimension as well as robust against noise and outliers. Experiments demonstrate the flexibility of the proposed algorithm.

References

  1. 1.

    Ballard DH: Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition 1981,13(2):111–122. 10.1016/0031-3203(81)90009-1

    MATH  Article  Google Scholar 

  2. 2.

    Ballester P: Applications of the Hough transform. In Astronomical Data Analysis Software and Systems III, ASP Conference Series Edited by: Barnes J, Crabtree DR, Hanisch RJ. 1994., 61:

    Google Scholar 

  3. 3.

    Barbarossa S: Analysis of multicomponent LFM signals by a combined Wigner-Hough transform. IEEE Transactions on Signal Processing 1995,43(6):1511–1515. 10.1109/78.388866

    Article  Google Scholar 

  4. 4.

    Bradley PS, Mangasarian OL:-plane clustering. Journal of Global Optimization 2000,16(1):23–32. 10.1023/A:1008324625522

    MathSciNet  MATH  Article  Google Scholar 

  5. 5.

    Chen SS, Donoho DL, Saunders MA: Atomic decomposition by basis pursuit. SIAM Journal of Scientific Computing 1998,20(1):33–61. 10.1137/S1064827596304010

    MathSciNet  MATH  Article  Google Scholar 

  6. 6.

    Cichocki A, Amari S: Adaptive Blind Signal and Image Processing. John Wiley & Sons, New York, NY, USA; 2002.

    Google Scholar 

  7. 7.

    Cirillo L, Zoubir A, Amin M: Direction finding of nonstationary signals using a time-frequency Hough transform. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), March 2005, Philadelphia, Pa, USA 2718–2721.

    Google Scholar 

  8. 8.

    Comon P: Independent component analysis. A new concept? Signal Processing 1994,36(3):287–314. 10.1016/0165-1684(94)90029-9

    MATH  Article  Google Scholar 

  9. 9.

    Donoho DL, Elad M:Optimally sparse representation in general (nonorthogonal) dictionaries via minimization. Proceedings of the National Academy of Sciences of the United States of America 2003,100(5):2197–2202. 10.1073/pnas.0437847100

    MathSciNet  MATH  Google Scholar 

  10. 10.

    Duda RO, Hart PE: Use of the Hough transformation to detect lines and curves in pictures. Communications of the ACM 1972,15(1):204–208.

    MATH  Article  Google Scholar 

  11. 11.

    Dudley RDepartment of Mathematics, MIT, course 18.465, 2005

  12. 12.

    Eriksson J, Koivunen V: Identifiability and separability of linear ica models revisited. Proceedings of the 4th International Symposium on Independent Component Analysis and Blind Source Separation (ICA '03), April 2003, Nara, Japan 23–27.

    Google Scholar 

  13. 13.

    Georgiev P, Pardalos P, Theis FJ, Cichocki A, Bakardjian H: Sparse component analysis: a new tool for data mining. In Data Mining in Biomedicine. Springer, New York, NY, USA; 2005. in print

    Google Scholar 

  14. 14.

    Georgiev P, Theis FJ, Cichocki A: Optimization algorithms for sparse representations and applications. In Multiscale Optimization Methods. Edited by: Pardalos P. Springer, New York, NY, USA; 2005.

    Google Scholar 

  15. 15.

    Georgiev P, Theis FJ, Cichocki A: Sparse component analysis and blind source separation of underdetermined mixtures. IEEE Transactions on Neural Networks 2005,16(4):992–996. 10.1109/TNN.2005.849840

    Article  Google Scholar 

  16. 16.

    Goldenshluger A, Zeevi A: The Hough transform estimator. Annals of Statistics 2004,32(5):1908–1932. 10.1214/009053604000000760

    MathSciNet  MATH  Article  Google Scholar 

  17. 17.

    Hough PVC: Machine analysis of bubble chamber pictures. In International Conference on High Energy Accelerators and Instrumentation, 1959, Geneva, Switzerland. CERN; 554–556.

    Google Scholar 

  18. 18.

    Hyvärinen A, Karhunen J, Oja E: Independent Component Analysis. John Wiley & Sons, New York, NY, USA; 2001.

    Google Scholar 

  19. 19.

    Hyvärinen A, Oja E: A fast fixed-point algorithm for independent component analysis. Neural Computation 1997,9(7):1483–1492. 10.1162/neco.1997.9.7.1483

    Article  Google Scholar 

  20. 20.

    Lee T-W, Lewicki MS, Girolami M, Sejnowski TJ: Blind source separation of more sources than mixtures using overcomplete representations. IEEE Signal Processing Letters 1999,6(4):87–90. 10.1109/97.752062

    Article  Google Scholar 

  21. 21.

    Lin JK, Grier DG, Cowan JD: Feature extraction approach to blind source separation. Proceedings of the IEEE Workshop on Neural Networks for Signal Processing (NNSP '97), September 1997, Amelia Island, Fla, USA 398–405.

    Google Scholar 

  22. 22.

    Rousseeuw PJ, Leroy AM: Robust Regression and Outlier Detection. John Wiley & Sons, New York, NY, USA; 1987.

    Google Scholar 

  23. 23.

    Shindo H, Hirai Y: An approach to overcomplete-blind source separation using geometric structure. In Proceedings of Annual Conference of Japanese Neural Network Society (JNNS '01), 2001, Nara, Japan. Naramachi Center; 95–96.

    Google Scholar 

  24. 24.

    Theis FJ: A new concept for separability problems in blind source separation. Neural Computation 2004,16(9):1827–1850. 10.1162/0899766041336404

    MATH  Article  Google Scholar 

  25. 25.

    Theis FJ, García GA: On the use of sparse signal decomposition in the analysis of multi-channel surface electromyograms. Signal Processing 2006,86(3):603–623. 10.1016/j.sigpro.2005.05.032

    MATH  Article  Google Scholar 

  26. 26.

    Theis FJ, Georgiev P, Cichocki A: Robust overcomplete matrix recovery for sparse sources using a generalized Hough transform. Proceedings of 12th European Symposium on Artificial Neural Networks (ESANN '04), April 2004, Bruges, Belgium 343–348. d-side, Evere, Belgium

    Google Scholar 

  27. 27.

    Theis FJ, Lang EW, Puntonet CG: A geometric algorithm for overcomplete linear ICA. Neurocomputing 2004,56(1–4):381–398.

    Article  Google Scholar 

  28. 28.

    Theis FJ, Puntonet CG, Lang EW: Median-based clustering for underdetermined blind signal processing. IEEE Signal Processing Letters 2006,13(2):96–99.

    Article  Google Scholar 

  29. 29.

    Waheed K, Salem F: Algebraic overcomplete independent component analysis. Proceedings of the 4th International Symposium on Independent Component Analysis and Blind Source Separation (ICA '03), April 2003, Nara, Japan 1077–1082.

    Google Scholar 

  30. 30.

    Zibulevsky M, Pearlmutter BA: Blind source separation by sparse decomposition in a signal dictionary. Neural Computation 2001,13(4):863–882. 10.1162/089976601300014385

    MATH  Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Fabian J. Theis.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Theis, F.J., Georgiev, P. & Cichocki, A. Robust Sparse Component Analysis Based on a Generalized Hough Transform. EURASIP J. Adv. Signal Process. 2007, 052105 (2006). https://doi.org/10.1155/2007/52105

Download citation

Keywords

  • Information Technology
  • Cost Function
  • Local Minimum
  • Quantum Information
  • Nonzero Element