Supervised Principal Geodesic Analysis on Facial Surface Normals for Gender Classification

  • Jing Wu
  • William A. P. Smith
  • Edwin R. Hancock
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5342)

Abstract

In this paper, we perform gender classification based on facial surface normals (facial needle-maps). We improve our previous work in [6] by using a non-Lambertian Shape-from-Shading (SFS) method to recover the surface normals, and develop a novel supervised principal geodesic analysis (PGA) to parameterize the facial needle-maps. Experimental results demonstrate the feasibility of gender classification based on facial needle-maps, and shows that incorporating pairwise relationships between the labeled data improves the gender discriminating powers in the leading PGA eigenvectors and gender classification accuracy.

References

  1. 1.
    Buchala, S., Davey, N., Gale, T., Frank, R.: Principal component analysis of gender, ethnicity, age, and identity of face images. In: IEEE ICMI 2005 (2005)Google Scholar
  2. 2.
    Lu, X., Chen, H., Jain, A.: Multimodal facial gender and ethnicity identification. In: ICB 2006, pp. 554–561 (2006)Google Scholar
  3. 3.
    Moghaddam, B., Yang, M.: Learning gender with support faces. IEEE Trans. on PAMI 24(5), 707–711 (2002)CrossRefGoogle Scholar
  4. 4.
    Bruce, V., Burton, A., Hanna, E., Healey, P., Mason, O., Coombes, A., Fright, R., Linney, A.: Sex discrimination: how do we tell the difference between male and female faces? Perception 22, 131–152 (1993)CrossRefGoogle Scholar
  5. 5.
    Burton, A., Bruce, V., Dench, N.: What’s the difference between men and women? evidence from facial measurement. Perception 22, 153–176 (1993)CrossRefGoogle Scholar
  6. 6.
    Wu, J., Smith, W., Hancock, E.: Gender classification using shape from shading. In: BMVC 2007, pp. 499–508 (2007)Google Scholar
  7. 7.
    Smith, W., Hancock, E.: A new framework for grayscale and colour non-lambertian shape-from-shading. In: ACCV 2007, pp. 869–880 (2007)Google Scholar
  8. 8.
    Torrance, K., Sparrow, E.: Theory for off-specular reflection from roughened surfaces. Journal of the Optical Society of America 57, 1105–1114 (1967)CrossRefGoogle Scholar
  9. 9.
    Fletcher, P., Joshi, S., Lu, C., Pizer, S.: Principal geodesic analysis for the study of nonlinear statistics of shape. IEEE Trans. on Medical Imaging 23, 995–1005 (2004)CrossRefGoogle Scholar
  10. 10.
    Pennec, X.: Probabilities and statistics on riemannian manifolds: A geometric approach. Technical Report RR-5093, INRIA (2004)Google Scholar
  11. 11.
    Koren, Y., Carmel, L.: Robust linear dimensionality reduction. IEEE Trans. on VCG 10(4) (2004)Google Scholar
  12. 12.
    Wu, J., Smith, W., Hancock, E.: Weighted principal geodesic analysis for facial gender classification. In: Rueda, L., Mery, D., Kittler, J. (eds.) CIARP 2007. LNCS, vol. 4756, pp. 331–339. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Sirovich, L.: Turbulence and the dynamics of coherent structures. Quart. Applied Mathematics XLV(3), 561–590 (1987)MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    Troje, N., Bulthoff, H.: Face recognition under varying poses: The role of texture and shape. Vision Research 36, 1761–1771 (1996)CrossRefGoogle Scholar
  15. 15.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: SIGGRAPH 1999 Conference Proceedings, pp. 187–194 (1999)Google Scholar
  16. 16.
    Martinez, A., Benavente, R.: The ar face database. CVC Technical Report (1998)Google Scholar
  17. 17.
    Devijver, P., Kittler, J.: Pattern Recognition: A Statistical Approach. PrenticeHall (1982)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Jing Wu
    • 1
  • William A. P. Smith
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Department of Computer ScienceThe University of YorkYorkUK

Personalised recommendations