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

Mona Omidyeganeh; Shahrokh Ghaemmaghami; Shervin Shirmohammadi

doi:10.1109/TIP.2011.2143421

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

IEEE Trans Image Process. 2011 Oct;20(10):2730-7. doi: 10.1109/TIP.2011.2143421. Epub 2011 Apr 19.

Authors

Mona Omidyeganeh¹, Shahrokh Ghaemmaghami, Shervin Shirmohammadi

Affiliation

¹ Department of Electrical Engineering, Sharif University of Technology and the Distributed and Collaborative Virtual Environment Research Lab., University of Ottawa, Ottawa, ON K1N6N5, Canada. m_omid@ee.sharif.edu

PMID: 21511566
DOI: 10.1109/TIP.2011.2143421

Abstract

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.