Integrated image content and metadata search and retrieval across multiple databases

  • Authors:
  • Matthew Addis;Mike Boniface;S. Goodall;Paul Grimwood;Sanghee Kim;Paul Lewis;Kirk Martinez;Alison Stevenson

  • Affiliations:
  • IT Innovation, University of Southampton, U. K;IT Innovation, University of Southampton, U. K;Department of Electronics and Computer Science, University of Southampton, Southampton, U. K;IT Innovation, University of Southampton, U. K;Department of Electronics and Computer Science, University of Southampton, Southampton, U. K;Department of Electronics and Computer Science, University of Southampton, Southampton, U. K;Department of Electronics and Computer Science, University of Southampton, Southampton, U. K;IT Innovation, University of Southampton, U. K

  • Venue:
  • CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an updated technical overview of an integrated content and metadata-based image retrieval system used by several major art galleries in Europe including the Louvre in Paris, the Victoria and Albert Museum in London, the Uffizi Gallery in Florence and the National Gallery in London. In our approach, the subjects of a query (e.g. images, textual metadata attributes), the operators used in a query (e.g. SimilarTo, Contains, Equals) and the rules that constrain the query (e.g. SimilarTo can only be applied to Images) are all explicitly defined and published for each gallery collection. In this way, cross-collection queries are dynamically constructed and executed in a way that is automatically constrained to the capabilities of the particular image collections being searched. The application of existing, standards based, technology to integrate metadata and content based queries underpins an open standards approach to extending interoperability across multiple image databases.