Weighted Principal Geodesic Analysis for Facial Gender Classification

  • Jing Wu
  • W. A. P. Smith
  • E. R. Hancock
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

In this paper, we describe a weighted principal geodesic analysis (WPGA) method to extract features for gender classification based on 2.5D facial surface normals (needle-maps) which can be extracted from 2D intensity images using shape-from-shading (SFS). By incorporating the weight matrix into principal geodesic analysis (PGA), we control the obtained principal axis to be in the direction of the variance on gender information. Experiments show that using WPGA, the leading eigenvectors encode more gender discriminating power than using PGA, and that gender classification based on leading WPGA parameters is more accurate and stable than based on leading PGA parameters.

Keywords

Gender classification facial surface normals principal geodesic analysis weighted principal geodesic analysis gender discriminating power 

References

  1. 1.
    Burton, A.M., Bruce, V., Dench, N.: What’s the Difference Between Men and Women? Evidence from Facial Measurement. Perception 22, 153–176 (1993)CrossRefGoogle Scholar
  2. 2.
    Buchala, S., Davey, N., Frank, R.J., Gale, T.M.: Dimensionality reduction of face images for gender classification. Department of Computer Science, The University of Hertfordshire, UK, Technical Report 408 (2004)Google Scholar
  3. 3.
    Buchala, S., Davey, N., Gale, T.M., Frank, R.J.: Principal Component Analysis of Gender, Ethnicity, Age, and Identity of Face Images. In: Proc. IEEE ICMI (2005)Google Scholar
  4. 4.
    Wilhelm, T., Bohme, H.J., Gross, H.M., Backhaus, A.: Statistical and Neural Methods for Vision-based Analysis of Facial Expressions and Gender. In: SMC 2004, pp. 2203–2208. IEEE omnipress (2004)Google Scholar
  5. 5.
    Wilhelm, T., Bohme, H.J., Gross, H.M.: Classification of Face Images for Gender, Age, Facial Expression, and Identity. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 569–574. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Lu, X., Chen, H., Jain, A.K.: Multimodal Facial Gender and Ethnicity Identification. In: ICB, HongKong, pp. 554–561 (2006)Google Scholar
  7. 7.
    Bruce, V., Burton, A.M., 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
  8. 8.
    Marr, D.: Vision. W.H. Freeman, San Francisco (1982)Google Scholar
  9. 9.
    Smith, W.A.P., Hancock, E.R.: Recovering Facial Shape and Albedo using a Statistical Model of Surface Normal Direction. Tenth IEEE International Conference on Computer Vision 1, 588–595 (2005)CrossRefGoogle Scholar
  10. 10.
    Fletcher, P.T., Joshi, S., Lu, C., Pizer, S.M.: Principal geodesic analysis for the study of nonlinear statistics of shape. IEEE Transactions on Medical Imaging 23, 995–1005 (2004)CrossRefGoogle Scholar
  11. 11.
    Pennec, X.: Probabilities and statistics on riemannian manifolds: A geometric approach. Technical Report RR-5093, INRIA (2004)Google Scholar
  12. 12.
    Sirovich, L.: Turbulence and the dynamics of coherent structures. Quart. Applied Mathematics XLV(3), 561–590 (1987)MathSciNetGoogle Scholar
  13. 13.
    Wu, J., Smith, W.A.P., Hancock, E.R.: Learning Mixture Models for Gender Classification based on Facial Surface Normals. In: IbPRIA 2007, vol. 4477, pp. 39–46 (2007)Google Scholar
  14. 14.
    Troje, N., Bulthoff, H.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.
    Devijver, P., Kittler, J.: Pattern Recognition: A Statistical Approach. Prentice Hall, Englewood Cliffs (1982)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Jing Wu
    • 1
  • W. A. P. Smith
    • 1
  • E. R. Hancock
    • 1
  1. 1.Department of Computer Science, The University of York, York, YO10 5DDUK

Personalised recommendations