Object-based queries using color points of interest

  • Authors:
  • V. Gouet;N. Boujemaa

  • Affiliations:
  • -;-

  • Venue:
  • CBAIVL '01 Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries (CBAIVL'01)
  • Year:
  • 2001

Quantified Score

Hi-index 0.03

Visualization

Abstract

Image retrieval systems based on the query-by-exampleparadigm usually imply a global description of the image.An approach involving points of interest has been developedand comes to light with object/sub-image retrieval taskswhich require more local descriptors. However this solution is not optimal, since it is limited to gray value images.We propose in this paper a local image descriptor based oncolor points of interest i.e. points extracted and characterized from color signal at once. This local characterization isthen involved in an image indexing and retrieval approachwhich is dedicated to object or sub-image retrieval. Theentire approach is evaluated on two image databases withvarious contents and some particular results of object retrieval show the relevance of our approach.