Free-hand sketch based image and video retrieval

  • Authors:
  • Rui Hu

  • Affiliations:
  • University of Surrey, Guildford, United Kingdom

  • Venue:
  • Proceedings of the international conference on Multimedia
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an overview of our work to date on a sketch based retrieval of image and video. We present a fast technique for extracting motion trajectories from videos and a Viterbi matching approach for retrieving video clips using free-hand sketched queries. For sketch based image retrieval, we introduce a depiction invariant image descriptor Gradient-Field-HOG (GF-HOG) that encapsulates local spatial structure in the sketch and facilitates efficient codebook based image retrieval driven by free-hand sketched queries. We further enhance the system with semantic information by incorporating user's search context.