Recognizing Faces from Head Rotation

Abstract

A new approach for recognizing human faces is presented that uses video sequences of natural, uncontrolled head rotations to capture face motion and dynamic appearance characteristics. Unlike traditional methods for face recognition that utilize one or a few static views, video is used for both training the face recognition system and for recognizing test faces. An algorithm is described that takes an uncalibrated video sequence and extracts the angular rotation of the head in each frame relative to the initial frame. A cropped window of the moving face is also computed, providing a dynamic appearance representation of the face together with the head motion description. Face recognition accuracy using this representation of rotating faces is shown for a small face video database, demonstrating the promise of the method.