Multi-View Face Alignment Using 3D Shape Model for View Estimation

  • Yanchao Su
  • Haizhou Ai
  • Shihong Lao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5558)

Abstract

For multi-view face alignment (MVFA), the non-linear variation of shape and texture, and the self-occlusion of facial feature points caused by view change are the two major difficulties. The state-of-the-art MVFA methods are essentially view-based approaches in which views are divided into several categories such as frontal, half profile, full profile etc. and each of them has its own model in MVFA. Therefore the view estimation problem becomes a critical step in MVFA. In this paper, a MVFA method using 3D face shape model for view estimation is presented in which the 3D shape model is used to estimate the pose of the face thereby selecting its model and indicating its self-occluded points. Experiments on different datasets are reported to show the improvement over previous works.

Keywords

Active Shape Model face alignment 3D face model 

References

  1. 1.
    Hill, A., Cootes, T.F., Taylor, C.J.: Active shape models and the shape approximation problem. In: BMVC 1995 (1995) Google Scholar
  2. 2.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Transactions on pattern analysis and machine intelligence 23(6) (June 2001) Google Scholar
  3. 3.
    Jiao, F., Li, S.Z., et al.: Face alignment using statistical models and wavelet features. In: CVPR 2003 (2003) Google Scholar
  4. 4.
    Zhang, L., Ai, H., et al.: Robust Face Alignment Based on Local Texture Classifiers. In: ICIP 2005 (2005) Google Scholar
  5. 5.
    Batur, A.U., Hayes, M.H.: A Novel Convergence for Active Appearance Models. In: CVPR 2003 (2003) Google Scholar
  6. 6.
    Cootes, T.F., Taylor, C.J.: A mixture model for representing shape variatio. In: BMVC 1997 (1997) Google Scholar
  7. 7.
    Romdhani, S., Gong, S., Psarrou, A.: A multi-view non-linear active shape model using kernel PCA. In: BMVC 1999 (1999) Google Scholar
  8. 8.
    Zhou, Y., Zhang, W., et al.: A Bayesian Mixture Model for Multi-view Face Alignment. In: CVPR 2005 (2005) Google Scholar
  9. 9.
    Li, S.Z., Yan, S.C., et al.: Multi-view face alignment using direct appearance models. In: AFG 2002 (2002) Google Scholar
  10. 10.
    Zhang, L., Ai, H.: Multi-View Active Shape Model with Robust Parameter Estimation. In: ICPR 2006 (2006) Google Scholar
  11. 11.
    Gu, L., Kanade, T.: 3D Alignment of Face in a Single Image. In: CVPR 2006 (2006) Google Scholar
  12. 12.
    Vogler, C., Li, Z.G., Kanaujia, A.: The Best of Both Worlds: Combining 3D Deformable Models with Active Shape Models. In: ICCV 2007 (2007) Google Scholar
  13. 13.
    The BJUT-3D Large-Scale Chinese Face Database. Technical Report No ISKL-TR-05-FMFR-001. Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory, Beijing University of Technology (2005) Google Scholar
  14. 14.
    Huang, C., Ai, H., et al.: High Performance Rotation Invariant Multiview Face Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(4), 671–686 (2007) Google Scholar
  15. 15.
    Sim, T., Baker, S., Bsat, M.: The CMU Pose, Illumination,and Expression (PIE) database of human faces. The roboticsinstitute, Carnegie Mellon University. Technical report (2001) Google Scholar
  16. 16.
    Huang, G.B., Ramesh, M., Berg, T., Miller, E.L.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 25(12), 7–49 (October 2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Yanchao Su
    • 1
  • Haizhou Ai
    • 1
  • Shihong Lao
    • 2
  1. 1.Computer Science and Technology DepartmentTsinghua UniversityChina
  2. 2.Core Technology CenterOmron CorporationJapan

Personalised recommendations