Abstract
In this paper, we introduced new adaptive learning algorithms to extract linear discriminant analysis (LDA) features from multidimensional data in order to reduce the data dimension space. For this purpose, new adaptive algorithms for the computation of the square root of the inverse covariance matrix Σ− 1/2 are introduced. The proof for the convergence of the new adaptive algorithm is given by presenting the related cost function and discussing about its initial conditions. The new adaptive algorithms are used before an adaptive principal component analysis algorithm in order to construct an adaptive multivariate multi-class LDA algorithm. Adaptive nature of the new optimal feature extraction method makes it appropriate for on-line pattern recognition applications. Both adaptive algorithms in the proposed structure are trained simultaneously, using a stream of input data. Experimental results using synthetic and real multi-class multi-dimensional sequence of data, demonstrated the effectiveness of the new adaptive feature extraction algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, New York (1990)
Chen, L., Liao, H.M., Ko, M., Lin, J., Yu, G.: A new LDA based face recognition system which can solve the small sample size problem. Pattern Recognition 33(10), 1713–1726 (2000)
Chellappa, R., Wilson, C.: Sirohey, Human and machine recognition of faces. Proc. IEEE 83(5), 705–740 (1995)
Yu, H., Yang, J.: A direct LDA algorithm for high-dimensional data with application to face recognition. Pattern Recog. 34(10), 2067–2070 (2001)
Mao, J., Jain, A.K.: Discriminant analysis neural networks. In: IEEE Int. Conf. on Neural Networks, CA, pp. 300–305 (1993)
Chatterjee, C., Roychowdhurry, V.P.: On self-organizing algorithm and networks for class separability features. IEEE Trans. Neural Network 8(3), 663–678 (1997)
Abrishami Moghaddam, H., Matinfar, M., Sajad Sadough, S.M., Amiri Zadeh, Kh.: Algorithms and networks for accelerated convergence of adaptive LDA. Pattern Recognition 38(4), 473–483 (2005)
Hongo, H., Yasumoto, N., Niva, Y., Yamamoto, K.: Hierarchical face recognition using an adaptive discriminant space. In: TENCON 2002. Proc. IEEE Int. Conf. Computers Communications, Control and Power Engineering, vol. 1, pp. 523–528. IEEE Computer Society Press, Los Alamitos (2002)
Rao, Y., Principe, N., Wong, J.C.: Fast RLS like algorithm for generalized eigen decomposition and its applications. Journal of VLSI Signal processing systems 37(3), 333–344 (2004)
Sanger, T.D.: Optimal unsupervised learning in a single-layer linear feed forward neural network. Neural Networks 2, 459–473 (1989)
Magnus, J.R., Neudecker, H.: Matrix Differential Calculus. John Wiley, Chichester (1999)
Widrow, B., Stearns, S.: Adaptive Signal Processing. Prentice-Hall, Englewood Cliffs (1985)
Ljung, L.: Analysis of recursive stochastic algorithms. IEEE Trans. Automat Control 22, 551–575 (1977)
Okada, T., Tomita, S.: An Optimal orthonormal system for discriminant analysis. Pattern Recognition 18(2), 139–144 (1985)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisher faces: Recognition using class specific linear projection. IEEE Trans. Pattern Anal. Machine Intel. 19, 711–720 (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ghassabeh, Y.A., Moghaddam, H.A. (2007). A New Incremental Optimal Feature Extraction Method for On-Line Applications. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2007. Lecture Notes in Computer Science, vol 4633. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74260-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-540-74260-9_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74258-6
Online ISBN: 978-3-540-74260-9
eBook Packages: Computer ScienceComputer Science (R0)