Shot boundary detection based on distance separability

Shot boundary detection is the first important task of content-based video retrieval. In this paper, a new SBD algorithm is proposed aiming to obtain accurate detection, and its performances are evaluated with different types of video. This algorithm computes distance ratio between within-class and between-class of two group frames, rather than the difference between two frames, which can resist light effects and camera/object movements in the same shot. The experimental results show that this universal algorithm can gain higher precision and recall.