Skip to main content
Log in

Recognising Simple Behaviours Using Time-Delay RBF Networks

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

This paper presents experiments using a radial basis function variant of the time-delay neural network with image sequences of human faces. The network is shown to be able to learn simple behaviours based on y-axis head rotation and generalise on different data. The network model's suitability for future dynamic vision applications is discussed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. H. Buxton and S. Gong, “Advanced visual surveillance using bayesian nets”, in J.L. Mundy and T. Strat (eds) Proc. of IEEE Workshop on Context-Based Vision, IEEE Computer Society Press: Cambridge, MA, 1995.

    Google Scholar 

  2. A. Psarrou and H. Buxton, “Hybrid architecture for understanding motion sequences”, Neurocomputing, Vol. 5, pp. 221–241, 1993.

    Google Scholar 

  3. M.I. Jordan, Serial order: A parallel, distributed processing approach, in J.L. Elman and D.E. Rumelhart (eds) Advances in Connectionist Theory: Speech, Lawrence Erlbaum: Hillsdale, NJ, 1989.

    Google Scholar 

  4. J. Elman, “Finding structure in time, Cognitive Science”, Vol. 14, pp. 179–211, 1990.

    Google Scholar 

  5. M.C. Mozer, “Neural net architectures for temporal sequence processing”, in A.S. Weigend and N.A. Gershenfeld (eds) Time Series Prediction: Predicting the Future and Understanding the Past, pp. 243–264, Addison-Wesley: Redwood City, CA, 1993.

    Google Scholar 

  6. J. Moody and C. Darken, “Learning with localized receptive fields”, in D. Touretzky, G. Hinton and T. Sejnowski (eds) Proc. 1988 Connectionist Models Summer School, pp. 133–143, Morgan Kaufmann: Pittsburgh, PA, 1988.

    Google Scholar 

  7. S. Ahmad and V. Tresp, “Some solutions to the missing feature problem in vision”, in S.J. Hanson, J.D. Cowan, and C.L. Giles (eds) Advances in Neural Information Processing Systems, Vol. 5, pp. 393–400, Morgan Kaufmann: Pittsburgh, PA, 1993.

    Google Scholar 

  8. C.M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press: Oxford, UK, 1995.

    Google Scholar 

  9. F. Girosi, “Some extensions of radial basis functions and their applications in artifical intelligence”, Computers & Mathematics with Applications, Vol. 24, No. 12, pp. 61–80, 1992.

    Google Scholar 

  10. A.J. Howell and H. Buxton, “Face recognition using radial basis function neural networks”, in Proc. British Machine Vision Conference, pp. 455–464, Edinburgh, BMVA Press, 1996.

    Google Scholar 

  11. A.J. Howell and H. Buxton, “Invariance in radial basis function neural networks in human face classification”, Neural Processing Letters, Vol. 2, No. 3, pp. 26–30, 1995.

    Google Scholar 

  12. A.J. Howell and H. Buxton, “A scaleable approach to face identification”, in Proc. International Conference on Artificial Neural Networks, Vol. 2, pp. 257–262, EC2 & Cie: Paris, France, 1995.

    Google Scholar 

  13. J.G. Daugman, “Complete discrete 2-D gabor transforms by neural networks for image analysis and compression”, IEEE Trans. Acoustics, Speech, & Signal Processing, Vol. 36, pp. 1169–1179, 1988.

    Google Scholar 

  14. J.A. Hertz, A. Krogh, and R.G. Palmer, Introduction to the Theory of Neural Computation, Addison-Wesley: Redwood City, CA, 1991.

    Google Scholar 

  15. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano and K. Lang, “Phoneme recognition using time-delay neural networks”, IEEE Trans. Acoustics, Speech, & Signal Processing, Vol. 37, pp. 328–339, 1989.

    Google Scholar 

  16. Y. Le Cun, B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard and L.D. Jackel, “Backpropagation applied to handwritten zip code recognition”, Neural Computation, Vol. 1, pp. 541–551, 1989.

    Google Scholar 

  17. J. Moody and C. Darken, “Fast learning in networks of locally-tuned processing units”, Neural Computation, Vol. 1, pp. 281–294, 1989.

    Google Scholar 

  18. M.R. Berthold, “A time delay radial basis function network for phoneme recognition”, in Proc. International Conference on Neural Networks, Vol. 7, pp. 4470–4473, Orlando, IEEE Computer Society Press, 1994.

    Google Scholar 

  19. A.J. Howell and H. Buxton, “Receptive field functions for face recognition”, in Proc. 2nd International Workshop on Parallel Modelling of Neural Operators for Pattern Recognition, pp. 83–92, University of Algarve, Faro, Portugal, 1995.

    Google Scholar 

  20. A.J. Howell and H. Buxton, “Towards unconstrained face recognition from image sequences”, in Proc. 2nd International Conference on Automatic Face & Gesture Recognition, pp. 224–229, Killington, VT, IEEE Computer Society Press, 1996.

    Google Scholar 

  21. A. Psarrou and H. Buxton, “Motion analysis with recurrent neural nets”, in Proc. International Conference on Artificial Neural Networks, Sorrento, Italy, Springer-Verlag: Berlin, 1994.

    Google Scholar 

  22. A. Cleeremans, “Finite state automata and simple recurrent networks”, Neural Computation, Vol. 1, pp. 372–381, 1989.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Howell, A.J., Buxton, H. Recognising Simple Behaviours Using Time-Delay RBF Networks. Neural Processing Letters 5, 97–104 (1997). https://doi.org/10.1023/A:1009657807312

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1009657807312

Navigation