Published on BOEMIE (http://www.boemie.org)
Objectives

BOEMIE will pave the way towards automation of the knowledge acquisition process from multimedia content which nowadays grows with increasing rates in both public and proprietary webs, and will break new ground by introducing and implementing the concept of evolving multimedia ontologies. The project is unique in that it links multimedia extraction with ontology evolution, creating a synergy of enormous yet unrealized potential. In recent years, significant advances have been made in the area of automatic extraction of low-level features from visual content. However, little progress has been achieved in the identification of high-level semantic features or the effective combination of semantic features derived from different modalities. Driven by domain-specific multimedia ontologies, BOEMIE information extraction systems will be able to identify high-level semantic features in image, video, audio and text and fuse these features for optimal extraction. The ontologies will be continuously populated and enriched using the extracted semantic content. This is a bootstrapping process, since the enriched ontologies will in turn be used to drive the multimedia information extraction system.



BOEMIE will demonstrate that by advancing the state of the art in each of the basic technologies towards convergence and cooperation, we can gain significant added value in terms of scalability and precision in knowledge acquisition from multimedia content. The rationale behind this approach is that multimedia information extraction can benefit in many ways from the background knowledge provided by ontologies, e.g. by placing a scene into context and reducing the space of alternatives for recognition. At the same time, semantic-level extraction from multimedia content provides a valuable source of information for the population and enrichment of ontologies, a principle which thus far has only been demonstrated in the case of textual content. Based on this clear motivation, it is natural to combine multimedia information extraction and ontology evolution in a common knowledge acquisition framework and to exploit the benefits of the resulting synergy.



The ambitious scope of the BOEMIE project and the proven specialized competence of the carefully composed project consortium ensure that the project will achieve the significant advancement of the state of the art needed to successfully implement the proposed approach. The long experience of the partners in past and current projects, where they have developed cutting edge technologies in the research areas of the project, provides the vehicle for driving technology to unexplored territories.

Valid XHTML 1.0 Transitional Valid CSS!

Source URL: http://www.boemie.org/objectives