Combinaison d'information visuelle, conceptuelle, et contextuelle pour la construction automatique de hierarchies semantiques adaptees a l'annotation d'images

TL;DR

This paper introduces a novel method for automatically constructing semantic hierarchies for image annotation by integrating visual, conceptual, and contextual information into a new similarity measure, enhancing classification accuracy.

Contribution

The paper presents a new semantic similarity measure combining multiple information sources and rules for hierarchy construction, improving image classification performance.

Findings

Hierarchies built with the new measure improve classification results.

The method effectively encodes hierarchical relationships between concepts.

Experiments demonstrate enhanced image annotation accuracy.

Abstract

This paper proposes a new methodology to automatically build semantic hierarchies suitable for image annotation and classification. The building of the hierarchy is based on a new measure of semantic similarity. The proposed measure incorporates several sources of information: visual, conceptual and contextual as we defined in this paper. The aim is to provide a measure that best represents image semantics. We then propose rules based on this measure, for the building of the final hierarchy, and which explicitly encode hierarchical relationships between different concepts. Therefore, the built hierarchy is used in a semantic hierarchical classification framework for image annotation. Our experiments and results show that the hierarchy built improves classification results. Ce papier propose une nouvelle methode pour la construction automatique de hierarchies semantiques adaptees a la classification et a l'annotation d'images. La construction de la hierarchie est basee sur une nouvelle mesure de similarite semantique qui integre plusieurs sources d'informations: visuelle, conceptuelle et contextuelle que nous definissons dans ce papier. L'objectif est de fournir une mesure qui est plus proche de la semantique des images. Nous proposons ensuite des regles, basees sur cette mesure, pour la construction de la hierarchie finale qui encode explicitement les relations hierarchiques entre les differents concepts. La hierarchie construite est ensuite utilisee dans un cadre de classification semantique hierarchique d'images en concepts visuels. Nos experiences et resultats montrent que la hierarchie construite permet d'ameliorer les resultats de la classification.