Developing Task-Specific RBF Hand Gesture Recognition

  • A. Jonathan Howell
  • Kingsley Sage
  • Hilary Buxton
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2915)


In this paper we develop hand gesture learning and recognition techniques to be used in advanced vision applications, such as the ActIPret system for understanding the activities of expert operators for education and training. Radial Basis Function (RBF) networks have been developed for reactive vision tasks and work well, exhibiting fast learning and classification. Specific extensions of our existing work to allow more general 3-D activity analysis reported here are: 1) action-based representation in a hand frame-of-reference by pre-processing of the trajectory data; 2) adaptation of the time-delay RBF network scheme to use this relative velocity information from the 3-D trajectory information in gesture recognition; and 3) development of multi-task support in the classifications by exploiting prototype similarities extracted from different combinations of direction (target tower) and height (target pod) for the hand trajectory.


Radial Basis Function Gesture Recognition Radial Basis Function Network Hand Trajectory Single Tower 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Basri, R.: Recognition by prototypes. IJ Computer Vision 19, 147–168 (1996)CrossRefGoogle Scholar
  2. 2.
    Beymer, D.J., Poggio, T.: Image representations for visual learning. Science 272, 1905–1909 (1996)CrossRefGoogle Scholar
  3. 3.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  4. 4.
    Buxton, H., Howell, A.J., Sage, K.: The role of task control and context in learning to recognise gesture. In: Cognitive Vision Workshop, Zürich (2002)Google Scholar
  5. 5.
    Duvdevani-Bar, S., Edelman, S., Howell, A.J., Buxton, H.: A similarity-based method for the generalization of face recognition over pose and expression. In: IEEE Int. Conf. Face Gesture Recognition, Nara, Japan, pp. 118–123 (1998)Google Scholar
  6. 6.
    Elman, J.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  7. 7.
    Feng, J., Sun, Y.L., Buxton, H.: Training the integrate-and-fire model with the Informax Principle II. IEEE Transactions on Neural Networks, 14 (2003) (accepted)Google Scholar
  8. 8.
    Gerstner, W.: Time structure of the activity in neural networks. Physical Review E 51, 738–758 (1995)Google Scholar
  9. 9.
    Howell, J., Buxton, H.: Invariance in radial basis function networks in human face classification. Neural Processing Letters 2, 26–30 (1995)CrossRefGoogle Scholar
  10. 10.
    Howell, J., Buxton, H.: Learning gestures for visually mediated interaction. In: British Machine Vision Conference, Southampton, UK (1998)Google Scholar
  11. 11.
    Howell, J., Buxton, H.: Learning identity with radial basis function networks. Neurocomputing 20, 15–34 (1998)CrossRefGoogle Scholar
  12. 12.
    Howell, J., Buxton, H.: Time-delay RBF networks for attentional frames in visually mediated interaction. Neural Processing Letters 15, 197–211 (2002)zbMATHCrossRefGoogle Scholar
  13. 13.
    Jordan, M.I.: Serial order: A parallel, distributed processing approach. In: Advances in Connectionist Theory: Speech. Lawrence Erlbaum, Mahwah (1989)Google Scholar
  14. 14.
    Moody, J., Darken, C.: Learning with localized receptive fields. In: Proc. 1988 Connectionist Models Summer School, pp. 133–143 (1988)Google Scholar
  15. 15.
    Moody, J., Darken, C.: Fast learning in networks of locally tuned processing units. Neural Computation 1, 281–294 (1989)CrossRefGoogle Scholar
  16. 16.
    Poggio, T., Edelman, S.: A network that learns to recognise three-dimensional objects. Nature 343, 263–266 (1990)CrossRefGoogle Scholar
  17. 17.
    Poggio, T., Girosi, F.: Regularisation algorithms for learning that are equivalent to multilayer networks. Science 247, 978–982 (1990)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Pomerleau, D.A.: ALVINN: An autonomous land vehicle in a neural network. In: NIPS, vol. 1, pp. 305–313 (1989)Google Scholar
  19. 19.
    Rosenblum, M., Yacoob, Y., Davis, L.D.: Human emotion recognition from motion using a RBF network architecture. IEEE TNN 7, 1121–1138 (1996)Google Scholar
  20. 20.
    Vetter, T., Poggio, T.: Image synthesis from a single example image. In: ECCV, Cambridge, UK, pp. 652–659 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • A. Jonathan Howell
    • 1
  • Kingsley Sage
    • 1
  • Hilary Buxton
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexBrightonUK

Personalised recommendations