Fuzzy Spatial Relation Ontology for Image Interpretation

Céline Hudelot 1 Jamal Atif 2, 3 Isabelle Bloch 4
3 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : The semantic interpretation of images can benefit from representations of useful concepts and the links between them as ontologies. In this paper, we propose an ontology of spatial relations, in order to guide image interpretation and the recognition of the structures it contains using structural information on the spatial arrangement of these structures. As an original theoretical contribution, this ontology is then enriched by fuzzy representations of concepts, which define their semantics, and allow establishing the link between these concepts (which are often expressed in linguistic terms) and the information that can be extracted from images. This contributes to reducing the semantic gap and it constitutes a new methodological approach to guide semantic image interpretation. This methodological approach is illustrated on a medical example, dealing with knowledge-based recognition of brain structures in 3D magnetic resonance images using the proposed fuzzy spatial relation ontology.
Type de document :
Article dans une revue
Fuzzy Sets and Systems, Elsevier, 2008, 159 (15), pp.1929-1951
Liste complète des métadonnées

Contributeur : Céline Hudelot <>
Soumis le : mercredi 22 mai 2013 - 10:13:19
Dernière modification le : mercredi 20 février 2019 - 14:41:46


  • HAL Id : hal-00824590, version 1


Céline Hudelot, Jamal Atif, Isabelle Bloch. Fuzzy Spatial Relation Ontology for Image Interpretation. Fuzzy Sets and Systems, Elsevier, 2008, 159 (15), pp.1929-1951. 〈hal-00824590〉



Consultations de la notice