Semantic Multimodal Analysis of Digital Media COST 292 Workshop

Abstract

In this paper we propose an algorithm to improve the re-<lb>sults of knowledge-assisted image analysis, based on con-<lb>textual information. In order to achieve this, we utilize fuzzy<lb>algebra, fuzzy sets and relations, towards efficient manipu-<lb>lation of image region concepts. We provide a novel context<lb>modelling, based on the OWL language, using RDF reifi-<lb>cation. Initial image analysis results are enhanced by the<lb>utilization of domain-independent, semantic knowledge in<lb>terms of concepts and relations between them. The novelty<lb>of the presented work is the context-driven re-adjustment<lb>of the degrees of confidence of the detected concepts pro-<lb>duced by any image analysis technique, utilizing a domain-<lb>independent ontology infrastructure to handle the knowl-<lb>edge, as well as multiple application domains.

Cite this paper

@inproceedings{Izquierdo2008SemanticMA, title={Semantic Multimodal Analysis of Digital Media COST 292 Workshop}, author={Ebroul Izquierdo and Leon van der Torre and Gian Mario Magio and Qianni Zhang and Naiara Aginako}, year={2008} }