3D face recognition using passive stereo vision

This paper proposes a face recognition system that uses (i) passive stereo vision to capture three-dimensional (3D) facial information and (ii) 3D matching using a simple ICP (iterative closest point) algorithm. So far, the reported 3D face recognition techniques assume the use of active 3D measurement for 3D facial capture. However, active methods employ structured illumination (structure projection, phase shift, gray-code demodulation, etc.) or laser scanning, which is not desirable in many human recognition applications. A major problem of using passive stereo vision for 3D measurement is its low accuracy, and thus no passive methods for 3D face recognition have been reported previously. Addressing this problem, we have newly developed a high-accuracy 3D measurement system based on passive stereo vision, where phase-based image matching is employed for sub-pixel disparity estimation. This paper presents the first attempt to create a practical face recognition system based on fully passive 3D reconstruction.

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

[2]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  C. D. Kuglin,et al.  The phase correlation image alignment method , 1975 .

[4]  Marc Acheroy,et al.  Automatic 3D face authentication , 2000, Image Vis. Comput..

[5]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[6]  T. Higuchi,et al.  High-Accuracy Subpixel Image Registration Based on Phase-Only Correlation , 2003, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[7]  Anil K. Jain,et al.  Deformation Analysis for 3D Face Matching , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.