Visual video summaries post-processing using supervised and unsupervised classification

Visual summaries allow users to grasp the overall content of a video, and access specific sequences within the video itself. The post-processing method presented in this paper makes it possible create exhaustive and not redundant visual video summaries. Three steps compose the method: the first removes the meaningless key frames; the second groups the key frames into clusters to allow multi-level summary presentation; and the third identifies the default summary level.