Face Recognition Using More than One Still Image: What Is More?

Abstract. While face recognition from a single still image has been extensively studied over a decade, face recognition based on more than one still image, such as multiple still images or a video sequence, is an emerging topic. Using more than one image introduces new recognition settings. In terms of recognition algorithm, multiple still images or a video sequence can be treated as a single still image in a degenerate manner. However, this treatment neglects additional properties present in multiple still images and/or video sequences. In this paper, we review three properties, manifested in multiple still images and/or video sequence, and their implications to different recognition settings. We also list corresponding approaches proposed in the literature that utilize these properties.

• Type: Conference
• Year: 2004
• Where: SINOBIOMETRICS
• Authors: Shaohua Kevin Zhou
• Keywords: Biometrics, Face Recognition, Images, SINOBIOMETRICS 2004, Video Sequence