Video Summary Based on F-Sift, Tamura Textural and Middle Level Semantic Feature
Rajnish K. Ranjan, Anupam Agrawal · Procedia Computer Science · 2016
The continuous generation of digital multimedia has raised the question about management of time and data. For effective management of such a tremendous amount of data or longer videos, a number of researches have been made. Video summarization is one of important research area to solve the problem. To summarise a video of any domain, researches relied on visual features available in frames, which does not guarantee to achieve semantic meaning of original video. In this paper, we proposed an approach for getting semantic video summary of original video. Generated video summaries are based on middle level semantic features, flip-Sift and tamura's textural feature. We used clustering approach based on middle level semantic features for static key frame extraction. Tamura feature has been used for getting texture features of frames. We tested this technique on various domains like sports, news, etc.; this technique has been tested on dataset freely available at YAACVID, UT egocentric and benchmark datasets. Longer duration video is also producing good result in compare to existing technique.