Abstract

This paper explores whether facial expressions can be recognised by using the distribution of surface normal directions in the extended Gaussian image (EGI). We work with range images and extract surface normals using a mesh fitting technique. Our representation of the surface normals is based on the co-efficients of spherical harmonics extracted from the EGI. We explore whether the co-efficients can be used to construct shape-spaces that capture variations in facial expression using a number of manifold learning techniques. Based on a comparison of various alternatives, the best results are given by the diffusion map.

Keywords

Facial Expression Spherical Harmonic Shape Descriptor Local Linear Embedding Kernel Principal Component Analysis 
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.

References

  1. 1.
    Hancock, E.R., Smith, W.A.P.: Recovering facial shape using a statistical model of surface normal direction. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(12), 1914–1930 (2006)CrossRefGoogle Scholar
  2. 2.
    Wu, J., Smith, W.A.P., Hancock, E.R.: Weighted principal geodesic analysis for facial gender classification. Progress in Pattern Recognition, Image Analysis and Applications, 331–339 (2007)Google Scholar
  3. 3.
    Bronstein, A., Bronstein, M., Kimmel, R.: Expression invariant face recognition via spherical embedding (2005)Google Scholar
  4. 4.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3d shape descriptors (2003)Google Scholar
  5. 5.
    Coifman, R.R., Lafon, S.: Diffusion maps. Applied and Computational Harmonic Analysis, 5–30 (2006)Google Scholar
  6. 6.
    Kim, K.I., Jung, K., Kim, H.J.: Face recognition using kernel principal component analysis. IEEE Signal Processing Letters 9(2) (2002)Google Scholar
  7. 7.
    Rowels, S., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  8. 8.
    Bai, X., Wilson, R.C., Hancock, E.R.: Manifold embedding of graphs using the heat kernel. Mathematics of Surfaces, 34–49 (2005)Google Scholar
  9. 9.
    Qiu, H., Hancock, E.R.: Graph embedding using commute time. Structural, Syntatic and Statistical Pattern Recognition, 441–449 (2006)Google Scholar
  10. 10.
    Horn, B.K.P.: Extended gaussian images. Proceedings of the IEEE 72(12), 1671–1686 (1984)CrossRefGoogle Scholar
  11. 11.
    Hobson, E.W.: The Theory of Spherical and Ellipsoidal Harmonics. Chelsea Publishing Company (1965)Google Scholar
  12. 12.
    Levy, B.: Laplace-beltrami eigenfunctions: Towards an algorithm that understands geometry (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • James Sharpe
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Department of Computer ScienceUniversity of YorkUK

Personalised recommendations