Photo retrieval combining ontology with visual information

  • Authors:
  • Sang-Kyun Kim

  • Affiliations:
  • Myongji University, Nam-dong Choin-gu Yongin-si

  • Venue:
  • Proceedings of the 2012 ACM Research in Applied Computation Symposium
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a method that effectively merges text information for an ontology with content-based image information is proposed to index and search photos based on their semantics. To achieve this goal, the method presents (1) semantic event clustering, (2) query expansion for retrieval, and (3) a method showing how to combine text query information with visual information in categories. Experimental results demonstrate that the proposed method sufficiently increases both the recall and mean average precision of retrieval results.