Human Face Modeling and Recognition Through Multi-View High Resolution Stereopsis

This paper presents a novel approach to face recognition that relies on 2D images to successfully reconstruct 3D shape of the human face. This approach ultimately outperforms 3D shape obtained from a commercial scanner. Additionally, our approach improves 2D recognition performance of 93.29% to 97.32%. Specifically, we employ multiple 2D views of a subject’s face to reconstruct several 3D models through binocular stereopsis. We use the ICP (Iterative Closest Point) algorithm to match the 3D probe to the 3D gallery for each view, thereby forming a voting committee of multiple members to determine the final matching score. We achieve an 85.23% rank-one recognition rate on our data set consisting of 149 distinct subjects, superior to the performance of a commercial 3D scanner. This is noteworthy given that our approach does not require strict calibration as in the case of the commercial 3D scanner. Also significant is the demonstrated flexibility of this system to successfully perform 3D recognition on a database acquired originally for 2D face recognition.