图象和视频的检索技术

A Survey of Technologies for Image and Video Indexing

随着网络技术的发展，多媒体数据将成为网络服务的主要内容，因此对多媒体数据管理问题的研究成为近几年的热点。由于媒体信息表现性质的不同，传统关系数据库的检索方式不再适用于图象和视频，因此，必须采用基于自身内容的检索方式。文章对基于内容的图象和视频检索技术分不同层次进行了全面的总结，内容包括依据基本特征，色彩、纹理、形状、和位置关系的技术，视频的场景分割、关键帧提取技术以及基于声音、文字的检索技术等，并阐述了各种方法的优缺点，现状及发展方向。

With the great development of networks,digital image and video will be the main contents that users request. The research on the management of multimedia database is now a hot field. However, the differences between visual and textual data in continuity and dimensicnality make traditional database unavailable for access to the stored multimedia information. The. paper surveys the techniques for content-based image and video indexing and retrieval hierarchically from feature - based, frame-based to object-based methods,including similarity measure~, compressed domain processing,video segmentation,video abstract,sound classification and text detection. It focuses on the integrated method and semantic analysis,and also presents author's ideas.