No abstract

No abstract

No abstract

No abstract

In this paper, the most recent version of the DIVAS system is presented. The system designs and develops a multimedia search engine based on advanced direct video and audio search techniques operating directly on compressed content. The basic scheme explores novel media content indexing and search technologies and integrates them into a scalable multimedia search engine. The developed algorithms facilitate for direct searching in large repositories of compressed audiovisual content, providing an alternative and complementary path for metadata based audio/video search. In addition, DIVAS adopts a module-based, expandable architecture, facilitating the ongoing expansion of the system based on researchers' contributions. In this study, the high-level architecture of the DIVAS system is provided, giving rise to the functional components of the main framework and the basic scheme incorporated for indexing and searching audiovisual repositories.