期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：6
出版社：S.S. Mishra
摘要：The continuous growth of computer technologies and Internet has made multimedia retrieval an active search area. Particularly searching for a video from massive video database effectively and accurately has become a challenging task. In this paper we provide a generic framework to find videos from a large database using feature extraction and annotations. Firstly video frames are extracted from the video and then low level feature of frames are extracted to store in video database. Secondly all the valid and related keywords and description are associated to the video and store them into database. On the basis of these feature vectors, tags and keywords that are stored in database, the proposed system retrieves the relevant videos from the database. The proposed system composed on the idea of content based video retrieval, low level feature extraction, search by text and search by example. Experimental results show that proposed method perform better than most of the video searching and reranking techniques in terms of both effectiveness and efficiency
关键词：Video search; color feature; content based video retrieval; feature extraction and annotation
