Abstract
This paper proposes a new face recognition approach by using Independent Component Analysis (ICA) and Hierarchical Radial Basis Function (HRBF) network classification model. To improve the quality of the face images, a series of image pre-processing techniques, which include histogram equalization, edge detection and geometrical transformation are used. The ICA based on Kernel Principal Component Analysis (KPCA) and FastICA is employed to extract features, and the HRBF network is used to identify the faces. To accelerate the convergence of the HRBF network and improve the quality of the solutions, the Extended Compact Genetic Programming (ECGP) and Particle Swarm Optimization (PSO) are applied to optimize the HRBF network structure and parameters. The experimental results show that the proposed framework is efficient for face recognition.
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
Zhang, C.P., Su, G.D.: Human Face Recognition: A survey. Journal of Image and Graphic 5(11), 885–894 (2000)
Yuille, A., Hallien, P.: Feature Extraction from Faces Using Deformable Templates. International Journal of Computer Vision 8(2), 99–111 (1992)
Zhao, W., Chellappa, R., Rosenfeld, A., Phillips, P.J.: Face Recognition: A Literature Survey. Technical Report CART-TR-948, University of Maryland (2002)
Hyvärinen, A., Karhunen, J.: Independent Component Analysis. Wiley, New York (2001)
Bartlett, M.S., Movellan, J.R., Sejnowski, T.J.: Face Recognition by Independent Component Analysis. IEEE Trans. Neural Networks 13(6), 1450–1464 (2002)
Valentin, D., Abdi, H., Toole, A.J.O., Cottrell, G.W.: Connectionist Models of Face Processing: A survey. Pattern Recognition 27, 1209–1230 (1994)
Er, M.J., Wu, S., Lu, J., Toh, H.L.: Face Recognition with Radial Basis Function (RBF) Neural Networks. IEEE Trans. Neural Network 13(3), 697–710 (2002)
Chen, X.L., Shan, S.G.: Pose-varied Face Recognition. Journal of Image and Graphics 4(10), 818–824 (1999)
Zhu, C.R., Wang, R.S.: Multi-pose Face Recognition Based on A Single View. Chinese Journal of Computers 26(1), 104–109 (2003)
Schölkopf, B., Smola, A., Muller, K.R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Comput. 10(5), 1299–1319 (1998)
Golub, G.H., Van Loan, C.F.: Matrix Computations, Thirded. The Johns Hopkins University Press, Baltimore (1996)
Mat Isa, N.A., Mashor, M.Y., Othman, N.H.: Diagnosis of Cervical Cancer using Hierarchical Radial Basis Function (HRBF) Network. In: Proceedings of the International Conference on Artificial Intelligence in Engineering and Technology, pp. 458–463 (2002)
Chen, Y.H., Peng, L.Z., Abraham, A.: Hierarchical Radial Basis Function Neural Networks for Classification Problems. In: Wang, J., Yi, Z., Zurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3971, pp. 873–879. Springer, Heidelberg (2006)
Sastry, K., Goldberg, D.E.: Probabilistic Model Building and Competent Genetic Programming. Genetic Programming Theory and Practise, 205–220 (2003)
Kennedy, J., Eberhart, R.: Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, pp. 1942–1948 (1995)
Su, H., Feng, D., Zhao, R.C.: Face Recognition Using Multi-feature and Radial Basis Function Network. In: Proc. of the Pan-Sydney Area Workshop on Visual Information Processing (VIP2002), Sydney, Australia, 183–189 (2002)
Huang, R., Pavlovic, V., Metaxas, D.N.: A Hybrid Face Recognition Method Using Markov Random Fields. ICPR04, pp. 157–160 (2004)
Schölkopf, B., Knirsch, P., Smola, C., Burges, A.: Fast Approximation of Support Vector Kernel Expansions, and an Interpretation of Clustering as Approximation in Feature Spaces. In: DAGM Symp. Mustererkennung. LNCS, pp. 124–132. Springer, Heidelberg (1998)
Franc, V., Hlavac, V.: Training Set Approximation for Kernel Methods. In: Proceedings of the 8th Computer Vision Winter Workshop, Prague, Czech Republic, pp. 121–126 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhou, J., Tang, H., Zhou, W. (2007). ICA Based on KPCA and Hierarchical RBF Network for Face Recognition. In: Huang, DS., Heutte, L., Loog, M. (eds) Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. ICIC 2007. Lecture Notes in Computer Science(), vol 4682. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74205-0_136
Download citation
DOI: https://doi.org/10.1007/978-3-540-74205-0_136
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74201-2
Online ISBN: 978-3-540-74205-0
eBook Packages: Computer ScienceComputer Science (R0)