NEW ADAPTIVE ALGORITHMS FOR OPTIMAL FEATURE EXTRACTION FROM GAUSSIAN DATA

Youness Aliyari Ghassabeh, Hamid Abrishami Moghaddam

2007

Abstract

In this paper, we present new adaptive learning algorithms to extract optimal features from multidimensional Gaussian data while preserving class separability. For this purpose, we introduce new adaptive algorithms for the computation of the square root of the inverse covariance matrix S - 1 2 . We prove the convergence of the adaptive algorithms by introducing the related cost function and discussing about its properties and initial conditions. Adaptive nature of the new feature extraction method makes it appropriate for on-line signal processing and pattern recognition applications. Experimental results using two-class multidimensional Gaussian data demonstrated the effectiveness of the new adaptive feature extraction method.

References

  1. S. Theodoridis, 2003, Pattern Recognition, Academic Press, New York, 2nd Edition.
  2. C. Chang, H. Ren, 2000, An Experimented-based quantitative and comparative analysis of target detection and image classification algorithms for hyper-spectral imagery, IEEE Trans. Geosci. Remote Sensing, Vol.38, No. 2, pp. 1044-1063.
  3. L. Chen, H. Mark Liao, J. Lin, M. Ko, G. Yu, 2000, A new LDA based face recognition system which can solve the small sample size problem, Pattern Recognition., No. 33, pp. 1713-1726.
  4. J, Lu, K. N. Plataniotis, A. N. Venetsanopoulos, 2003, Face recognition using LDA-based algorithms, IEEE Trans. Neural Networks, Vol. 14, No.1, pp. 195-200.
  5. C. Chatterjee, V.P. Roychowdhury, 1997, On selforganizing algorithm and networks for classseparability features, IEEE Trans. Neural Network, Vol. 8, No.3, pp 663-678.
  6. H. Abrishami Moghaddam, Kh. Amiri Zadeh, 2003, Fast adaptive algorithms and networks for classseparability features, Pattern Recognition, Vol. 36, No. 8, pp. 1695-1702.
  7. H.Abrishami Moghaddam, M.Matinfar, S.M. Sajad Sadough, Kh. Amiri Zadeh, 2005, Algorithms and networks for accelerated convergence of adaptive LDA, Pattern Recognition, Vol. 38, No. 4, pp. 473- 483.
  8. K. Fukunaga, 1990, Introduction to Statistical Pattern Recognition, Academic Press, New York, 2nd Edition.
  9. J.R. Magnus, H. Neudecker, 1999, Matrix Differential Calculus, John Wiley.
  10. B.Widrow, S. Stearns, 1985, Adaptive Signal Processing, Prentice-Hall.
  11. M. Hagan, H. Demuth, 2002, Neural Network Design, PWS Publishing Company.
  12. H. J. Kushner, D. S. Clarck, 1978, Stochastic approximatiom methods for constrained and unconstrained systems, Speringer Verlog.
  13. A. Benveniste, M. Metivier, P. Priouret, 1990, Adaptive algorithms and stochastic approximations, Academic Press, New York, 2nd Edition.
  14. L. Ljung, 1977, Analysis of recursive stochastic algorithms , IEEE Trans. Automat Control, Vol. 22, pp. 551-575, Aug. 1977.
  15. S. Ozawa, S. L. Toh, S. Abe, S. Pang, N. Kasabov, 2005, Incremental learning of feature space and classifier for face recognition, Neural Networks, Vol. 18, pp. 575- 584.
  16. S. Pang, S. Ozawa, N. Kasabov, 2005, Incremental linear discriminant analysis for classification of data streams”, IEEE Trans. on Systems, Man and Cybernetics, Vol. 35, No. 5, pp. 905-914.
  17. T. Okada, S.Tomita, 1985, An Optimal orthonormal system for discriminant analysis, Pattern Recognition, Vol. 18, No.2, pp. 139-144.
Download


Paper Citation


in Harvard Style

Aliyari Ghassabeh Y. and Abrishami Moghaddam H. (2007). NEW ADAPTIVE ALGORITHMS FOR OPTIMAL FEATURE EXTRACTION FROM GAUSSIAN DATA . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Mathematical and Linguistic Techniques for Image Mining, (VISAPP 2007) ISBN 978-972-8865-75-7, pages 182-187. DOI: 10.5220/0002067501820187


in Bibtex Style

@conference{mathematical and linguistic techniques for image mining07,
author={Youness Aliyari Ghassabeh and Hamid Abrishami Moghaddam},
title={NEW ADAPTIVE ALGORITHMS FOR OPTIMAL FEATURE EXTRACTION FROM GAUSSIAN DATA},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Mathematical and Linguistic Techniques for Image Mining, (VISAPP 2007)},
year={2007},
pages={182-187},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002067501820187},
isbn={978-972-8865-75-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Mathematical and Linguistic Techniques for Image Mining, (VISAPP 2007)
TI - NEW ADAPTIVE ALGORITHMS FOR OPTIMAL FEATURE EXTRACTION FROM GAUSSIAN DATA
SN - 978-972-8865-75-7
AU - Aliyari Ghassabeh Y.
AU - Abrishami Moghaddam H.
PY - 2007
SP - 182
EP - 187
DO - 10.5220/0002067501820187