Efficient video indexing scheme for content-based retrieval

Extracting a small number of key frames that can abstract the content of vi deo is very important for efficient browsing and retrieval in video databas es. In this paper, the key frame extraction problem is considered from a se t-theoretic point of view, and systematic algorithms are derived to find a compact set of key frames that can represent a video segment for a given de gree of fidelity. The proposed extraction algorithms can be hierarchically applied to obtain a tree-structured key frame hierarchy that is a multileve l abstract of the video. The key frame hierarchy enables an efficient conte nt-based retrieval by using the depth-first search scheme with pruning. Int ensive experiments on a variety of video sequences are presented to demonst rate the improved performance of the proposed algorithms over the existing approaches.