Building a 3D Morphable Face Model by Using Thin Plate Splines for Face Reconstruction

In this paper, we introduce a semi-automatic deformation alignment method, Thin Plate Spline, to generate a 3D morphable face model from 3D face data This model includes an average 3D face on both shape and texture, and a set of morphable coefficients for individual sample faces A primary 3D morphable face model based on Chinese people is then set up Simulation results show the feasibility of this 3D morphable model for 2D face recognition on with different PIE in future research.

[1]  Thomas Vetter,et al.  Face Recognition Based on Fitting a 3D Morphable Model , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Yuxiao Hu,et al.  Automatic 3D reconstruction for face recognition , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[3]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[5]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[6]  Shuicheng Yan,et al.  Multi-view face alignment using direct appearance models , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.