CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2009 vol.31 Issue No.12 - December
Issue No.12 - December (2009 vol.31)
Carlos D. Castillo , University of Maryland, College Park
David W. Jacobs , University of Maryland, College Park
Face recognition across pose is a problem of fundamental importance in computer vision. We propose to address this problem by using stereo matching to judge the similarity of two, 2D images of faces seen from different poses. Stereo matching allows for arbitrary, physically valid, continuous correspondences. We show that the stereo matching cost provides a very robust measure of similarity of faces that is insensitive to pose variations. To enable this, we show that, for conditions common in face recognition, the epipolar geometry of face images can be computed using either four or three feature points. We also provide a straightforward adaptation of a stereo matching algorithm to compute the similarity between faces. The proposed approach has been tested on the CMU PIE data set and demonstrates superior performance compared to existing methods in the presence of pose variation. It also shows robustness to lighting variation.
Face recognition, pose, stereo matching, epipolar geometry.
Carlos D. Castillo, David W. Jacobs, "Using Stereo Matching with General Epipolar Geometry for 2D Face Recognition across Pose", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 12, pp. 2298-2304, December 2009, doi:10.1109/TPAMI.2009.123