Publication

Abstract : Video shot boundary is an early stage of content based video analysis and is fundamental to any kind to of video application. The increased availability and usage of online digital video has created a need for automated video content analysis techniques. Major bottle neck that limits a wider use of digital video is the ability of quickly finding desired information from a huge database. Manual indexing and annotating the video material are both computationally expensive and time consuming. In this paper we design a novel approach for shot boundary detection using visual attention model by comparing the saliency measures. The approach is robust to a wide range of digital effects with low computational complexity