Video retrieval based on key frame extraction in compressed domain

This paper proposes a new key frame extraction algorithm and also provides a novel video-indexing scheme for fast content-based browsing and retrieval in a video database. The algorithm is designed to function with a compressed video stream. We first extract key frames by matching AHIM (Accumulated Histogram Intersection Measure) of DC image sequence constructed from the MPEG video sequence. Then we use the region segmentation-based projective histogram and its moments as database indices for video retrieval. From the simulation results, the proposed method clearly shows the validity and superiority in respect of computation time and memory space, and that in conjunction with other techniques for indexing, such as color, can provide a powerful framework for image indexing and retrieval.