A framework for content-based image retrieval fully exploiting the semantics of annotation

We present a framework and an application for semanticbased retrieval of images. Our approach adopts a two-level ontology structure in a subset of OWL-DL. In the core ontology only generic spatial relations are represented, while domain ontologies are specific for the image collection. The approach allows semantic-based relevence ranking and results explanation for query refinement, by exploiting standard and non-standard inferences in Description Logics.

• Type: Conference
• Year: 2006
• Where: SAC
• Authors: Tommaso Di Noia, Eugenio Di Sciascio, Francesco di Cugno, Eufemia Tinelli, Francesco M. Donini
• Keywords: Applied Computing, Core Ontology, Generic Spatial Relations, SAC 2006, Two-level Ontology Structure