Loading...

Video keyframe analysis using a segment-based statistical metric in a visually sensitive parametric space

Omidyeganeh, M ; Sharif University of Technology | 2011

746 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TIP.2011.2143421
  3. Publisher: 2011
  4. Abstract:
  5. This paper addresses a new approach to the keyframe extraction problem employing generalized Gaussian density (GGD) parameters of wavelet transform subbands along with Kullback-Leibler distance (KLD) measurement. Shot and cluster boundaries are selected using KLDs between GGD feature vectors, and then keyframes are located based on similarity and dissimilarity criteria. Objective and subjective evaluations show the high accuracy of this new approach compared with traditional methods
  6. Keywords:
  7. Generalized Gaussian density (GGD) ; Kullback-Leibler distance (KLD) ; video keyframe extraction ; Cluster boundaries ; Feature vectors ; Key-frame extraction ; Key-frames ; Parametric spaces ; Segment-based ; Sub-bands ; Subjective evaluations ; Wavelet transforms
  8. Source: IEEE Transactions on Image Processing ; Volume 20, Issue 10 , Oct , 2011 , Pages 2730-2737 ; 10577149 (ISSN)
  9. URL: http://www.ncbi.nlm.nih.gov/pubmed/21511566