3D face recognition based on matching of facial surfaces

Face recognition is an important task in pattern recognition and computer vision. In this work a method for 3D face recognition in the presence of facial expression and poses variations is proposed. The method uses 3D shape data without color or texture information. A new matching algorithm based on conformal mapping of original facial surfaces onto a Riemannian manifold followed by comparison of conformal and isometric invariants computed in the manifold is suggested. Experimental results are presented using common 3D face databases that contain significant amount of expression and pose variations.

[1]  L. Akarun,et al.  A 3D Face Recognition System for Expression and Occlusion Invariance , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[2]  Wei Zeng,et al.  Surface matching and registration using symmetric conformal mapping , 2009, 2009 11th IEEE International Conference on Computer-Aided Design and Computer Graphics.

[3]  Faisal R. Al-Osaimi,et al.  An Expression Deformation Approach to Non-rigid 3D Face Recognition , 2009, International Journal of Computer Vision.

[4]  Anil K. Jain,et al.  Deformation Modeling for Robust 3D Face Matching , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Pierre Alliez,et al.  Spectral Conformal Parameterization , 2008, Comput. Graph. Forum.

[6]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[7]  Maurício Pamplona Segundo,et al.  3D Face Recognition Using Simulated Annealing and the Surface Interpenetration Measure , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Sen Wang,et al.  Conformal Geometry and Its Applications on 3D Shape Matching, Recognition, and Stitching , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Jae-Chang Shim,et al.  Curvature based human face recognition using depth weighted Hausdorff distance , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[10]  Liming Chen,et al.  A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[11]  Bruno Lévy,et al.  Least squares conformal maps for automatic texture atlas generation , 2002, ACM Trans. Graph..

[12]  Mark Meyer,et al.  Discrete Differential-Geometry Operators for Triangulated 2-Manifolds , 2002, VisMath.

[13]  Mohammed Bennamoun,et al.  Keypoint Detection and Local Feature Matching for Textured 3D Face Recognition , 2007, International Journal of Computer Vision.

[14]  Paul Suetens,et al.  A Comparative Study of 3-D Face Recognition Under Expression Variations , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).