Skip to Main Content
In this paper, a motion and similarity-based fake detection algorithm is presented for biometric face recognition systems. First, an input video is segmented into foreground and background regions. Second, the similarity is measured between a background region, i.e., a region without a face and upper body, and an original background region recorded at an initializing stage. Third, a background motion index is calculated to indicate the amount of motion in the background region compared with the motion in the foreground region. By combining the result of similarity and the result of the background motion index, a fake video can be detected robustly with a regular USB camera.