An efficient video similarity search strategy for video-on-demand systems

Abstract

The video-on-demand systems and video share web are more and more popular in recent years. Video similarity search for content-based video retrieval is important in web service and research field. There is still no satisfying search method for scalable fast similarity search in large video database. In order to solve two challenging problems: video similarity measure and fast search method in large database, a novel efficient video similarity search strategy for video-on-demand systems is proposed in this paper. A compact video signature was computed according to image histogram and spatial-temporal features of video. The video similarity is measured by the computation of the distance of video signature. For the scalable computing requirement, a new search method based on Clustering Index Table was presented by index clustering. The experimental results from the query tests in large database show this method is highly efficient and effective for similar video search.