CAIM - Context Aware Image Management

-

In the CAIM project we introduce image context-awareness as a means of supporting image-based information retrieval in distributed and mobile environments. An image can be associated with multiple contexts and knowledge of these contexts can enhance the q uality of the information retrieval process. We believe that context-awareness can be used for identifying image semantics and relationships, and may thus contribute to closing the semantic gap between user information requests and the shortcomings of cur rent content-based image retrieval techniques. The CAIM project will focus on research and the development of tools for context-aware image management, where image description, query formulation, retrieval from heterogeneous distributed environments, an d ranking are designed for using context information. Important application domains are those requiring image capture and multimodal retrieval in mobile environments. An objective in the CAIM project is to design a system that is flexible enough to suppo rt context-aware image management for a vide variety of applications. To do so, a component-based architecture, using components and component frameworks, will form the basis for a context-aware image management system. The project will develop a prototyp e implementation of a context-aware image management system and a set of end-user applications that demonstrate the usefulness of CAIM concepts. The research builds on previous research at University of Tromsø, University of Bergen, Munich University of T echnology, Univ. of Hawaii at Manoa and Telenor R&D in the areas of data management, image processing, information retrieval, multimedia and mobile systems.