3D Face Recognition Based on G-H Shape Variation

  • Chenghua Xu
  • Yunhong Wang
  • Tieniu Tan
  • Long Quan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3338)


Face recognition has been an interesting issue in pattern recognition over the past few decades. In this paper, we propose a new method for face recognition using 3D information. During preprocessing, the scanned 3D point clouds are first registered together, and at the same time, the regular meshes are generated. Then the novel shape variation representation based on Gaussian-Hermite moments (GH-SVI) is proposed to characterize an individual. Experimental results on the 3D face database 3DPEF, with complex pose and expression variations, and 3D_RMA, likely the largest 3D face database currently available, demonstrate that the proposed features are very important to characterize an individual.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhao, W., Chellappa, R., Phillips, P.J., Rosenfeld, A.: Face Recognition: A Literature Survey. ACM Computing Surveys (CSUR) archive 35(4), 399–458 (2003)CrossRefGoogle Scholar
  2. 2.
    Lee, J.C., Milios, E.: Matching Range Images of Human Faces. In: Proc. ICCV 1990, pp. 722–726 (1990)Google Scholar
  3. 3.
    Gordon, G.G.: Face Recognition Based on Depth and Curvature Features. In: Proc. CVPR 1992, pp. 108–110 (1992)Google Scholar
  4. 4.
    Yacoob, Y., Davis, L.S.: Labeling of Human Face Components from Range Data. CVGIP: Image Understanding 60(2), 168–178 (1994)CrossRefGoogle Scholar
  5. 5.
    Chua, C.S., Han, F., Ho, Y.K.: 3D Human Face Recognition Using Point Signature. In: Proc. FG 2000, pp. 233–239 (2000)Google Scholar
  6. 6.
    Beumier, C., Acheroy, M.: Automatic Face Authentication from 3D Surface. In: Proc. BMVC 1998, pp. 449–458 (1998)Google Scholar
  7. 7.
    Beumier, C., Acheroy, M.: Automatic 3D Face Authentication. Image and Vision Computing 18(4), 315–321 (2000)CrossRefGoogle Scholar
  8. 8.
    Tanaka, H.T., Ikeda, M., Chiaki, H.: Curvature-based Face Surface Recognition Using Spherical Correlation. In: Proc. FG 1998, pp. 372–377 (1998)Google Scholar
  9. 9.
    Hesher, C., Srivastava, A., Erlebacher, G.: A Novel Technique for Face Recognition Using Range Imaging. Inter. Multiconference in Computer Science (2002)Google Scholar
  10. 10.
    Lee, Y., Park, K., Shim, J., Yi, T.: 3D Face Recognition Using Statistical Multiple Features for the Local Depth Information. In: Proc. 16th Inter. Conf. on Vision Interface (2003)Google Scholar
  11. 11.
    Liao, S., Pawlak, M.: On Image Analysis by Moments. IEEE Trans. on PAMI 18(3), 254–266 (1996)Google Scholar
  12. 12.
    Shen, J., Shen, W., Shen, D.: On Geometric and Orthogonal Moments. Inter. Journal of Pattern Recognition and Artificial Intelligence. 14(7), 875–894 (2000)CrossRefGoogle Scholar
  13. 13.
    Xu, C., Wang, Y., Tan, T., Quan, L.: A Robust Method for Detecting Nose on 3D Point Cloud. In: Proc. ICIP 2004 (2004) (to appear)Google Scholar
  14. 14.
    Besl, P.J., Mckay, N.D.: A Method for Registration of 3-D shapes. IEEE Trans. PAMI. 14(2), 239–256 (1992)Google Scholar
  15. 15.
    Xu, C., Quan, L., Wang, Y., Tan, T., Lhuillier, M.: Adaptive Multi-resolution Fitting and its Application to Realistic Head Modeling. IEEE Geometric Modeling and Processing, 345–348 (2004)Google Scholar
  16. 16.
    Chua, C.S., Jarvis, R.: Point Signatures: A New Representation for 3-D Object Recognition. IJCV 25(1), 63–85 (1997)CrossRefGoogle Scholar
  17. 17.
    Hoffman, R.L., Jain, A.K.: Segmentation and Classification of Range Images. IEEE Trans. on PAMI 9(5), 608–620 (1987)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Chenghua Xu
    • 1
  • Yunhong Wang
    • 1
  • Tieniu Tan
    • 1
  • Long Quan
    • 2
  1. 1.National Laboratory of Pattern Recognition, Institute of AutomationCASBeijingP. R. China
  2. 2.Department of Computer ScienceHong Kong University of Science and TechnologyKowloon, Hong Kong

Personalised recommendations