Towards an Illumination-Based 3D Active Appearance Model for Fast Face Alignment

A novel 3D active appearance model invariant to illumination is presented. 3D-IAAM(Tridimensional Illumination-based Active Appearance Model) is capable of representing human faces with any identity, pose and illumination condition and it was tested for face synthesis by creating faces with multiple identities, poses and illuminations. We also propose an illumination-invariant 3D face alignment algorithm based on our model which is suitable for fast estimation of 3D pose and structure of faces. In this work, we model the illumination to do the alignment, instead of eliminating its effects, with the possibility of obtaining additional information about the original lighting at the end of the fitting process.

[1]  Fadi Dornaika,et al.  Fast and reliable active appearance model search for 3-D face tracking , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[3]  Ronen Basri,et al.  Lambertian Reflectance and Linear Subspaces , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  David J. Kriegman,et al.  Nine points of light: acquiring subspaces for face recognition under variable lighting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Takeo Kanade,et al.  Real-time combined 2D+3D active appearance models , 2004, CVPR 2004.

[6]  Stephen Lin,et al.  Face alignment under variable illumination , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[7]  Bernd Neumann,et al.  Computer Vision — ECCV’98 , 1998, Lecture Notes in Computer Science.

[8]  David J. Kriegman,et al.  Face Recognition Using 3-D Models: Pose and Illumination , 2006, Proceedings of the IEEE.

[9]  Rasmus Larsen,et al.  An Active Illumination and Appearance (AIA) Model for Face Alignment , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  A. Sattar,et al.  Face Alignment by 2.5D Active Appearance Mo del Optimized by Simplex , 2007 .

[11]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Simon Baker,et al.  Active Appearance Models Revisited , 2004, International Journal of Computer Vision.

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