Abstract
This paper is concerned with the types of invariance exhibited by Radial Basis Function (RBF) neural networks when used for human face classification, and the generalisation abilities arising from this behaviour. Experiments using face images in ranges from face-on to profile show the RBF network's invariance to 2-D shift, scale and y-axis rotation. Finally, the suitability of RBF techniques for future, more automated face classification purposes is discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J. Moody, C. Darken. Learning with localized receptive fields, in D. Touretzky, G. Hinton, T. Sejnowski, eds,Proc. 1988 Connectionist Models Summer School, Morgan Kaufmann, pp. 133–143, 1988.
T. Poggio, F. Girosi. Regularization algorithms for learning that are equivalent to multilayer networks,Science, no. 247, pp. 978–982, 1990.
F. Girosi. Some extensions of radial basis functions and their applications in artifical intelligence,Computers Math. Applic., vol. 24, no. 12, pp. 61–80, 1992.
M. T. Musavi, W. Ahmad, K. H. Chan, K. B. Faris, D. M. Hummels. On the training of radial basis function classifiers,Neural Networks, vol. 5, pp. 595–603, 1992.
S. Ahmad, V. Tresp. Some solutions to the missing feature problem in vision. In S. J. Hanson, J. D. Cowan, C. L. Giles, eds,Adv. in Neural Information Processing Systems, vol. 5, Morgan Kaufmann, 1993.
V. Bruce, A. Young. Understanding face recognition,British Journal of Psychology, no. 77, pp. 305–327, 1986.
V. Bruce.Recognising Faces, Lawrence Erlbaum Associates, 1988.
H. D. Ellis, A. W. Young. Are faces special? In A. W. Young, H. D. Ellis, eds,Handbook of Research on Face Processing, North-Holland, 1989.
D. C. Hay, A. Young. The human face. In H. D. Ellis, ed.,Normality and Pathology in Cognitive Functions, Academic Press, 1982.
D. C. Hay, A. Young, A. W. Ellis. Routes through the face recognition system,Q. Journal of Experimental Psychology, vol. 43, pp. 761–791, 1991.
S. Chen, C. F. N. Cowan, P. M. Grant. Orthogonal least squares learning algorithm for radial basis function networks,IEEE Trans. on Neural Networks, vol. 2, pp. 302–309, 1991.
J. A. Hertz, A. Krogh, R. G. Palmer.Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.
A. J. Howell, H. Buxton. Invariance in radial basis function neural networks in human face classification,Technical Report CSRP 365, School of Cognitive and Computing Sciences, University of Sussex, 1995.
D. Marr.Vision, Freeman, 1982.
K. Stokbro, D. K. Umberger, J. A. Hertz. Exploiting neurons with localized receptive fields to learn chaos,Complex Systems, vol. 4, pp. 603–622, 1990.
M. Turk, A. Pentland. Eigenfaces for recognition,Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Howell, A.J., Buxton, H. Invariance in radial basis function neural networks in human face classification. Neural Process Lett 2, 26–30 (1995). https://doi.org/10.1007/BF02311576
Issue Date:
DOI: https://doi.org/10.1007/BF02311576