Skip to main content
SpringerLink
Log in

Using RBF networks to map GWT ridge images to pose

  • Session F3A: Face and Hand Posture Recognition
  • Conference paper
  • First Online:
Book cover Computer Vision — ACCV'98 (ACCV 1998)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1351))

Included in the following conference series:

  • 128 Accesses

Abstract

A Pose estimation system is proposed that uses an RBF network to map Gabor Wavelet Transformations (GWT) of faces to a pose angle. In particular we show (a) how the functional description of the GWT face images can be used for their parameterisation and reduction of their dimensionality and (b) how the dimensionality reduced GWT images can lead to the definition of a ridge pose space V where the face representations are sparsified and the distance measure in V correlates well with the perceived image similarity.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. P. Belhumeur and et al. “Eigenfaces vs fisherfaces: Recognition using class specific linear projection”. In ECCV'96.

    Google Scholar 

  2. C.M. Bishop. Networks for pattern recognition. Oxford University Press, 1995.

    Google Scholar 

  3. R. Brunelli and T. Poggio. “Face recognition: Features versus templates”. IEEE PAMI, 15(10):1042–1052, October 1993.

    Google Scholar 

  4. R. Chellapa, C.L. Wilson, and S. Sirohey. “Human and machine recognition of faces: A survey”. Proceedings of the IEEE, 83:705–740, 1995.

    Google Scholar 

  5. J. G. Daugman. “Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filters”. J. Opt. Soc. Am., pages 1160–1169, 1985.

    Google Scholar 

  6. B. Duc, S. Fischer, and J. Bigün. “Face authentification with sparse grid Gabor information”. In Proc. IEEE Int. Conf. ASSP, 1997.

    Google Scholar 

  7. S. Fischer, B. Duc, and J. Bigün. “Face recognition with Gabor phase and dynamic link matching for multi-modal identification”. Technical Report LTS 96.04, Signal Proc. Lab., Swiss Federal Inst. of Technology, 1996.

    Google Scholar 

  8. F. Girosi. “Some extensions of radial basis functions and their applications in artificial intelligence”. Computers and Mathematics with Applications, 24(12):6180, 1992.

    Google Scholar 

  9. S. Gong, S.J. McKenna, and J.J. Collins. “An investigation into face pose distributions”. In Proc. 2nd ICAFGR, Vermont, 1996.

    Google Scholar 

  10. S. Gong, A. Psarrou, and et al. “Head tracking and dynamic face recognition”. In European Workshop on Combined Real and Synthetic Image Processing for Broadcast and Video Production, Hamburg, Germany, 1994.

    Google Scholar 

  11. A.J. Howell and H. Buxton. “Towards unconstraint face recognition from image sequences”. In Proc of the 2nd ICAFGR, Vermont, October 1996.

    Google Scholar 

  12. N. Krüger and et al. “Determination of face position and pose with a learned representation based on labeled graphs”. Technical Report 96-03, Institut für Neuroinformatik, Ruhr-Universität Bochum, January 1996.

    Google Scholar 

  13. M. Lades and et al. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42(3):300–311, 1993.

    Google Scholar 

  14. T. Maurer and C. von der Malsburg. “Tracking and learning graphs on image sequences of faces”. In Proc. ICANN, Bochum, 1996.

    Google Scholar 

  15. S.J. McKenna and S. Gong. “Real-time face pose estimation”. Submitted to Real Time Imaging Journal March 1997.

    Google Scholar 

  16. S.J. McKenna, S. Gong, R. Würtz, J. Tanner, and D. Banin. “Tracking facial feature points with Gabor wavelets and shape models”. In Proc. Audio-and video-based biometric person authentification, pages 35–42, 1997.

    Google Scholar 

  17. A. Pentland, B. Moghaddam, and T. Starner. “View-based and modular eigenspaces for face recognition”. In IEEE Proc. on CVPR, 1994.

    Google Scholar 

  18. A. Psarrou, S. Gong, and H. Buxton. “Modelling Spatio-temporal Trajectories and Face Signatures on Partially Recurrent Neural Networks”. In IEEE ICNN, Perth, Australia, 1995.

    Google Scholar 

  19. M. Turk and A. Pentland. “Eigenfaces for recognition”. Journal of Cognitive Neuroscience, 3(1), 1991.

    Google Scholar 

  20. L. Wiskott, J.M. Fellous, N. Krüger, and C. von der Malburg. “Face recognition and gender determination”. In IWAFGR, Zurich, 1995.

    Google Scholar 

  21. R.P. Würtz. “Multilayer dynamic link networks for establishing image point correspondences and visual object recognition”. Verlag Harri Deutsch, 1995.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science, University of Westminster, Harrow Campus, Watford Road, Northwick Park, Harrow HAI 3TP, London, UK

    Alexandra Psarrou & Jonathan Tanner

Authors
  1. Alexandra Psarrou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jonathan Tanner
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Roland Chin Ting-Chuen Pong

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Psarrou, A., Tanner, J. (1997). Using RBF networks to map GWT ridge images to pose. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63930-6_180

Download citation

  • DOI: https://doi.org/10.1007/3-540-63930-6_180

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63930-5

  • Online ISBN: 978-3-540-69669-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation