Abstract
In this paper we introduce a set of adaptive vision techniques which could be used, for example, in video-conferencing applications. First, we present methods for finding faces and selecting attentional frames to focus visual processing. Second, we present methods for recognising individual gesture phases for camera control. Finally, we discuss how these techniques can be extended to ‘virtual groups’ of multiple people interacting at multiple sites.
Similar content being viewed by others
References
Bobick, A. F.: Movement, activity, and action: The role of knowledge in the perception of motion. Proceedings of Royal Society London, Series B, 352, 1257–1265, 1997.
Buxton, H. and Gong, S.: Visual surveillance in a dynamic and uncertain world, Artificial Intelligence, 78 (1995), 431–459.
Cutler, R. and Turk, M.: View-based interpretation of real-time optical flow for gesture recognition. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan, IEEE Computer Society Press, (1998), pp. 416–421.
Daugman, J. G.: Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression. IEEE Transactions on Acoustics, Speech, and Signal Processing, 36 (1988), 1169–1179.
Elman, J.: Finding structure in time. Cognitive Science, 14 (1990), 179–211.
Howell, A. J.: Automatic face recognition using radial basis function networks. PhD thesis, University of Sussex, 1997.
Howell, A. J.: Face recognition using RBF networks. In: R. J. Howlett and Jain (eds.), Radial Basis Function Networks 2: New Advances in Design. Physica-Verlag, (2001), pp. 103–142.
Howell, A. J. and Buxton, H.: Towards unconstrained face recognition from image sequences. In: Proceedings of International Conference on Automatic Face and Gesture Recognition, Killington, VT, IEEE Computer Society Press, (1996), pp. 224–229.
Howell, A. J. and Buxton, H.: Recognising simple behaviours using time-delay RBF networks. Neural Processing Letters, 5 (1997), 97–104.
Howell, A. J. and Buxton, H.: Learning gestures for visually mediated interaction. In: P. H. Lewis and M. S. Nixon (eds.), Proceedings of British Machine Vision Conference, Southampton, UK, BMVA Press, (1998), pp. 508–517.
Howell, A. J. and Buxton, H.: Learning identity with radial basis function networks. Neurocomputing, 20 (1998), 15–34.
Jordan, M. I.: 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).
McKenna, S. J. and Gong, S.: Gesture recognition for visually mediated interaction using probabilistic event trajectories. In: P. H. Lewis and M. S. Nixon (eds.), Proceedings of British Machine Vision Conference, Southampton, UK, BMVA Press, (1998), pp. 498–507.
McKenna, S. J. Gong, S. and Raja, Y.: Face recognition in dynamic scenes. In: A. F. Clark (ed.), Proceedings of British Machine Vision Conference, Colchester, UK, BMVA Press, (1997), pp. 140–151.
Moody, J. and Darken, C.: Learning with localized receptive fields. In: D. Touretzky, G. Hinton, and T. Sejnowski (eds.), Proceedings of 1988 Connectionist Models Summer School, Pittsburgh, PA, Morgan Kaufmann, (1988), pp. 133–143.
Moody, J. and Darken, C.: Fast learning in networks of locally-tuned processing units. Neural Computation, 1 (1989), 281–294.
Moses, Y. Adini, Y. and Ullman, S.: Face recognition: the problem of compensating for illumination changes. In: J. O. Eklundh (ed.), Proceedings of European Conference on Computer Vision, Lecture Notes in Computer Science, Vol. 800, Stockholm, Sweden, Springer-Verlag, (1994), pp. 286–296.
Mozer, M. C.: 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, Addison-Wesley, Redwood City, CA, (1994), pp. 243–264.
Pentland, A.: Smart rooms. Scientific American, 274(4) (1996), 68–76.
Poggio, T. and Edelman, S.: A network that learns to recognize three-dimensional objects. Nature, 343 (1990), 263–266.
Poggio, T. and Girosi, F.: Regularization algorithms for learning that are equivalent to multilayer networks. Science, 247 (1990), 978–982.
Pomerleau, D. A.: ALVINN: An autonomous land vehicle in a neural network. In: D. S. Touretzky, (ed.), Advances in Neural Information Processing Systems, Vol. 1, San Mateo, CA, Morgan Kaufmann (1989), pp. 305–313.
Rosenblum, M. and Davis, L. S.: An improved radial basis function network for autonomous road-following. IEEE Transactions on Neural Networks, 7 (1996), 1111–1120.
Rowley, H. A., Baluja, S. and Kanade, T.: Human face detection in visual scenes. In: D. S. Touretzky, M. C. Mozer and M. E. Hasselmo (eds.), Advances in Neural Information Processing Systems, Vol. 8, Cambridge, MA, MIT Press, (1996), pp. 875–881.
Sherrah, J. and Gong, S.: Exploiting context in gesture recognition. In: P. Bouquet, L. Serafini, P. Brézillon, M. Benerecetti and F. Castellani (eds.), Modelling and Using Context, Proceedings of Second International and Interdisciplinary Conference, CONTEXT'99, Lecture Notes in Artificial Intelligence, Vol. 1688, Trento, Italy, Springer-Verlag, (1999), pp. 515–518.
Sherrah, J., Gong, S., Howell, A. J. and Buxton, H.: Interpretation of group behaviour in visually mediated interaction. In: Proceedings of 15th International Conference on Pattern Recognition, Barcelona, Spain, (2000), pp. 266–269.
Turk, M.: Visual interaction with lifelike characters. In: Proceedings of International Conference on Automatic Face and Gesture Recognition, Killington, VT, IEEE Computer Society Press, (1996), pp. 368–373.
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K. and Lang, K.: Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37 (1989), 328–339.
Wren, C. R. and Pentland, A. P.: Dynamic models of human motion. In: Proceedings of IEEE International Conference on Automatic Face & Gesture Recognition, Nara, Japan, IEEE Computer Society Press, (1998), pp. 22–27.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Howell, A.J., Buxton, H. RBF Network Methods for Face Detection and Attentional Frames. Neural Processing Letters 15, 197–211 (2002). https://doi.org/10.1023/A:1015743231018
Issue Date:
DOI: https://doi.org/10.1023/A:1015743231018