Image Retrieval by Ontological Description of Shapes (IRONS), Early Results

  • Authors:
  • Affiliations:
  • Venue:
  • CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper addresses the problem of retrievingdocuments that contain visual information. Currentvisual information retrieval systems sometimesretrieve irrelevant documents or documents unrelatedto the userýs query. This problem is caused by the useof low-level image descriptors; furthermore, thesedescriptors hardly have a semantic weight. In thiswork we address the image retrieval problem basedon shape, since shape has a meaning by itself. On theother hand, an extension of the ontology concept,which is used in information retrieval based on text,is proposed in the image domain. Likewise, wepresent the Image Retrieval by OntologicalDescription of Shapes (IRONS) System. IRONS hasbeen implemented and evaluated in order to analyzeits utility, efficiency, and advantages comparing withwell-known systems.