Visual diversification of image search results

  • Authors:
  • Reinier H. van Leuken;Lluis Garcia;Ximena Olivares;Roelof van Zwol

  • Affiliations:
  • Universiteit Utrecht, Utrecht, Netherlands;Yahoo! Research, Barcelona, Spain;Unversitat Pompeu Fabra, Barcelona, Spain;Yahoo! Research, Barcelona, Spain

  • Venue:
  • Proceedings of the 18th international conference on World wide web
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Due to the reliance on the textual information associated with an image, image search engines on the Web lack the discriminative power to deliver visually diverse search results. The textual descriptions are key to retrieve relevant results for a given user query, but at the same time provide little information about the rich image content. In this paper we investigate three methods for visual diversification of image search results. The methods deploy lightweight clustering techniques in combination with a dynamic weighting function of the visual features, to best capture the discriminative aspects of the resulting set of images that is retrieved. A representative image is selected from each cluster, which together form a diverse result set. Based on a performance evaluation we find that the outcome of the methods closely resembles human perception of diversity, which was established in an extensive clustering experiment carried out by human assessors.