Advertisement

Face Recognition Using RBF Networks

  • A. J. Howell
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 67)

Abstract

We present an example-based approach to learning several recognition tasks using pose-varying face data. We show how computationally cheap radial basis function (RBF) classifiers can be developed for three separate, static recognition tasks, identity, expression and pose, with the same training data. The flexibility of such an approach means that, provided an appropriate representation is chosen for the data, re-learning for new tasks is both practical and computationally efficient.

Keywords

Radial Basis Function Face Recognition Face Image Scale Invariance Radial Basis Function Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Ahmad, S. and Tresp, V. (1993), “Some solutions to the missing feature problem in vision,” in Hanson, S.J., Cowan, J.D., and Giles, C.L. (Eds.), Advances in Neural Information Processing Systems, vol. 5, Morgan Kaufmann, San Mateo, CA, pp. 393–400.Google Scholar
  2. [2]
    Beymer, D.J. and Poggio, T. (1996), “Image representations for visual learning,” Science, vol. 272, pp. 1905–1909.CrossRefGoogle Scholar
  3. [3]
    Bishop, C.M. (1995), Neural Networks for Pattern Recognition, Oxford University Press, Oxford, U.K.Google Scholar
  4. [4]
    Broomhead D.S. and Lowe, D. (1988), “Multivariable functional interpolation and adaptive networks,” Complex Systems, vol. 2, pp. 321–355.MathSciNetMATHGoogle Scholar
  5. [5]
    Bruce, V., Valentine, T., and Baddeley, A.D. (1987), “The basis of the 3/4 view advantage in face recognition,” Applied Cognitive Psychology, vol. 1, pp. 109–120.CrossRefGoogle Scholar
  6. [6]
    Bruce, V. and Young, A. (1986), “Understanding face recognition,” British Journal of Psychology, vol. 77, pp. 305–327.Google Scholar
  7. [7]
    Brunelli, R. and Poggio, T. (1991), “HyperBF networks for real object recognition,” in Myopoulos, J. and Reiter, R. (Eds.) Proceedings of International Joint Conference on Artificial IntelligenceMorgan Kaufmann, Sydney, Australia, pp. 1278–1284. Google Scholar
  8. [8]
    Chen, S., Cowan, C.F.N., and Grant P.M. (1991), “Orthogonal least squares learning algorithm for radial basis function networks,” IEEE Transactions on Neural Networks, vol. 2, pp. 302–309.CrossRefGoogle Scholar
  9. [9]
    Duvdevani-Bar, S., Edelman, S., Howell, A.J., and Buxton, H. (1998), “A similarity-based method for the generalization of face recognition over pose and expression,” in Proceedings of IEEE International Conference on Automatic Face and Gesture RecognitionIEEE Computer Society Press, Nara, Japan, pp. 118–123. Google Scholar
  10. [10]
    Edelman, S., Reisfeld, D., and Yeshurun, Y. (1992), “Learning to recognize faces from examples,” in Sandini, G. (Ed.) Proceedings of European Conference on Computer Vision Lecture Notes in Computer Sciencevol. 588, Springer-Verlag, Santa Margherita Ligure, Italy, pp. 787–791. Google Scholar
  11. [11]
    Girosi, F. (1992), “Some extensions of radial basis functions and their applications in artificial intelligence,” Computers and Mathematics with Applicationsvol. 24, pp.61–80. Google Scholar
  12. [12]
    Gong, S., McKenna, S.J., and Collins, J.J. (1996), “An investigation into face pose distributions,” in Proceedings of International Conference on Automatic Face and Gesture RecognitionIEEE Computer Society Press, Killington, VT, pp. 265–270. Google Scholar
  13. [13]
    Hay, D.C. and Young, A. (1982), “The human face,” in Ellis, H.D. (Ed.), Normality and Pathology in Cognitive Functions, Academic Press, San Diego, CA.Google Scholar
  14. [14]
    Howell, A.J. (1997), Automatic face recognition using radial basis function networks, Ph.D. thesis, University of Sussex.Google Scholar
  15. [15]
    Howell, A.J. (1999), “Face unit radial basis function networks,” in Jain, L.C., Halici, U., Hayashi, I., Lee, S.B., and Tsutsui, S. (Eds.) Intelligent Biometric Techniques in Fingerprint and Face RecognitionCRC Press, pp. 315–334. Google Scholar
  16. [16]
    Howell, A.J. (1999), “Introduction to face recognition,” in Jain, L.C., Halici, U., Hayashi, I., Lee, S.B., and Tsutsui, S. (Eds.) Intelligent Biometric Techniques in Fingerprint and Face RecognitionCRC Press, pp. 217–284. Google Scholar
  17. [17]
    Howell, A.J. and Buxton, H. (1996), “Face recognition using radial basis function neural networks,” in Fisher, R.B. and Trucco, E. (Eds.), Proceedings of British Machine Vision Conference, BMVA Press, Edinburgh, pp. 455–464.Google Scholar
  18. [18]
    Howell, A.J. and Buxton, H. (1998), “Recognising people and behaviours,” in Wechsler, H., Philips, P.J., Bruce, V., FogelmanSoulié, F, and Huang, T. (Eds.) Face Recognition: from Theory to Applications NATO ASI Series FSpringer-Verlag. Google Scholar
  19. [19]
    McKenna, S.J. and Gong, S. (1996), “Tracking faces,” Proceedings of International Conference on Automatic Face and Gesture RecognitionIEEE Computer Society Press, Killington, VT, pp. 271–276. Google Scholar
  20. [20]
    McKenna, S.J., Gong, S., and Collins, J.J. (1996), “Face tracking and pose representation,” in Fisher, R.B. and Trucco, E. (Eds.) Proceedings of British Machine Vision ConferenceBMVA Press, Edinburgh, pp. 755–764. Google Scholar
  21. [21]
    Moody, J. and Darken, C. (1988), “Learning with localized receptive fields,” in Touretzky, D., Hinton, G., and Sejnowski, T. (Eds.), Proceedings of 1988 Connectionist Models Summer School,Morgan Kaufmann, Pittsburgh, PA, pp. 133–143.Google Scholar
  22. [22]
    Moody, J. and Darken, C. (1989), “Fast learning in networks of locally-tuned processing units,” Neural Computation, vol. 1, pp. 281–294.CrossRefGoogle Scholar
  23. [23]
    Moses, Y., Adini, Y., and Ullman, S. (1994), “Face recognition: the problem of compensating for illumination changes,” in Eklundh, J.O. (Ed.), Proceedings of European Conference on Computer Vision, Lecture Notes in Computer Science, vol. 800, Springer-Verlag, Stockholm, Sweden, pp. 286–296.Google Scholar
  24. [24]
    Musavi, M.T., Ahmad, W., Chan, K.H., Faris, K.B., and Hummels, D.M. (1992), “On the training of radial basis function classifiers,” Neural Networks, vol. 5, pp. 595–603.Google Scholar
  25. [25]
    Poggio, T. and Edelman, S. (1990), “A network that learns to recognize three-dimensional objects,” Nature, vol. 343, pp. 263–266.CrossRefGoogle Scholar
  26. [26]
    Poggio, T. and Girosi, F. (1990), “Networks for approximation and learning,” Proceedings of IEEE, vol. 78, pp. 1481–1497.CrossRefGoogle Scholar
  27. [27]
    Poggio, T. and Girosi, E (1990), “Regularization algorithms for learning that are equivalent to multilayer networks,” Science, vol. 247, pp. 978–982.MathSciNetMATHCrossRefGoogle Scholar
  28. [28]
    Pomerleau, D.A. (1989), “ALVINN: an autonomous land vehicle in a neural network,” in Touretzky, D.S. (Ed.), Advances in Neural Information Processing Systems, Morgan Kaufmann, San Mateo, CA, vol. 1, pp. 305–313.Google Scholar
  29. [29]
    Press, W.H., Flannery, B.P., Teukolsky, S.A., and Vetterling, W.T. (1986), Numerical Recipes in C, Cambridge University Press, Cambridge.Google Scholar
  30. [30]
    Rosenblum, M. and Davis, L.S. (1996), “An improved radial basis function network for autonomous road-following,” IEEE Transactions on Neural Networks, vol. 7, pp. 1111–1120.CrossRefGoogle Scholar
  31. [31]
    Saha, A. and Keeler, J.D. (1990), “Algorithms for better representation and faster learning in radial basis function networks,” in Touretzky, D.S. (Ed.), Advances in Neural Information Processing Systems, Morgan Kaufmann, San Mateo, CA, vol. 2.Google Scholar
  32. [32]
    Stokbro, K., Umberger, D.K., and Hertz, J.A. (1990), “Exploiting neurons with localized receptive fields to learn chaos,” Complex Systems, vol. 4, pp. 603–622.MATHGoogle Scholar
  33. [33]
    Ullman, S. and Basri, R. (1991), “Recognition by linear combinations of models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, pp. 992–1006.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • A. J. Howell

There are no affiliations available

Personalised recommendations