Pose-invariant face recognition using cylindrical model and stereo camera

This paper proposes a pose-invariant face recognition method using a cylindrical model and a stereo camera. We divided this paper into two parts. One is a single input image case and the other is a stereo input image case. In the single input image case, we normalized a face´s yaw pose using cylindrical model, and in the stereo input image case, we normalized a face´s pitch pose using cylindrical model with estimated object´s pitch pose by stereo geometry. Also, since we have the advantage that we can utilize two images acquired at the same time, we can increase overall recognition rate by decision-level fusion. By experiments, we confirmed that recognition rate could be increased using our methods.