Unterstanding Video Retrieval- Approaches to Bridge the Semantic Gap Evaluation Strategies and State-of-the-Art Systems

With the improving capabilities of current hardware systems there are evergrowing possibilities to store and manipulate videos in a digital formatleading to a growing number of video archives. People build their own digitallibraries from materials created through digital cameras and camcorders anduse systems such as YouTube to place this material on the web.Unfortunately this data creation prowess is not matched by any comparabletools to organise and retrieve video information. There is a need to createnew retrieval engines to assist the users in searching and finding video scenesthey would like to see from many different video files. Unlike text retrievalsystems retrieval on digital video datasets is facing a serious problem: TheSemantic Gap. This is the difference between low-level data representation ofvideos and the higher level concepts user associates with video. This bookintroduces several approaches to bridge this semantic gap explains differentevaluation strategies and presents state-of-the-art video retrieval tools. Thetarget audience is everyone who is interested in getting to know the researchapproaches that led to the popular video retrieval tools.