Image-Based 3D Face Modeling from Stereo Images

  • Kyongpil Min
  • Junchul Chun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3980)


This paper presents an automatic and novel method to generate a realistic 3D face model from stereo images. Typically, an image-based 3D face modeling system is in need of human intervention in facial feature extraction stage. To remove this human intervention, we propose HT(Hue-Tint) skin color model for facial feature extraction. Based on the proposed chrominance model, we can detect facial region and extract facial feature positions. Subsequently, the facial features are adjusted by using edge information of the detected facial region along with the proportions of the face. Moreover, the proposed facial extraction method can effectively eliminate the epipolar constraints caused by using stereo vision approach. In order to produce a realistic 3D face model, we adopt RBF(Radial-Based Function) to deform the generic face model according to the detected facial feature points from stereo images. For deformation locality parameter of RBF is critical since it can have significant impact on the quality of deformation. Thus, we propose new parameter decision rule that is applicable to scattered data interpolation. It makes clusters of feature points to detect points under the influence of each width parameter. From the experiments, we can show the proposed approach efficiently detects facial feature points and produces a realistic 3D face model.


Feature Point Facial Feature Face Detection Stereo Image Width Parameter 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Parke, F.I.: A parameteric model for human faces. PhD thesis. University of Utah, salt Lake City, UT (1974)Google Scholar
  2. 2.
    Pighin, F., Hecker, J., Lischinski, D., Szeliski, R., Salesin, D.H.: Synthesizing realistic facial expressions from photographs. In: Proceedings of Computer Graphics SIGGRAPH 1998, pp. 231–242 (1998)Google Scholar
  3. 3.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of Computer Grphics, SIGGRAPH 1999 Conference, pp. 187–194 (1999)Google Scholar
  4. 4.
    Enciso, R., Li, J., Fidaleo, D., Kim, T.Y., Noh, J.Y., Neumann, U.: Synthesis of 3D faces. In: Proc. Int. Workshop on Digital and Computational Video (1999)Google Scholar
  5. 5.
    Min, K., Chun, J., Park, G.: A Nonparametric Skin Color Model for Face Detection from Color Images. In: Liew, K.-M., Shen, H., See, S., Cai, W. (eds.) PDCAT 2004. LNCS, vol. 3320, pp. 115–119. Springer, Heidelberg (2004)Google Scholar
  6. 6.
    Barnard, S.T., Fischler, M.A.: Computational Stereo. ACM Computing Surveys (CSUR) 14(4), 553–572 (1982)CrossRefGoogle Scholar
  7. 7.
    Noh, J., Neumann, U.: A survey of facial modeling and animation techniques. Tech. rep., USC 99-705 (1998)Google Scholar
  8. 8.
    Wirth, M.A.: A Nonrigid Approach to Medical Image Registration: Matching Images of the Breast. Ph.D. Thesis. RMIT University Melbourne Australia (2000)Google Scholar
  9. 9.
    Lyche, T., Schumaker, L.: Scattered Data Interpolation in Three or More Variables. In: Mathematical Methods in Computer Aided Geometric Design, pp. 1–33. Academic Press, London (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kyongpil Min
    • 1
  • Junchul Chun
    • 1
  1. 1.Department of Computer ScienceKyonggi UniversityYui-Dong SuwonKorea

Personalised recommendations