• Jayabharathy
• Renu

Video summarization is to produce a video chunk by removing the duplications and preserving the most representative content in the original video. A Video Summary consists of a single shot with relatively consistent high-level semantics and emotional content. To extract a summary from a long sequence of video, a few representative segments are generally sufficient. These representative segments could be selected based on the segment-level semantic and emotional recognition. The input video is segmented as frames and clustered based on a similarity of frames. Each cluster is then analyzed based on semantic analysis and emotion recognition. The existing system addresses only the emotion recognition for video summary generation whereas the proposed system generates video summary based on semantic analysis and facial emotion recognition. Moreover, the proposed system also considers the most representative audio(text) for video generation. From the video human facial expression is detected and trained by GABOR filter. The detected features are classified by Relevance Vector Machine (RVM) classification technique. The proposed algorithm reduces the time complexity and provides accurate emotion detection. The experimental results prove that the video summary generated through our framework gives an efficient summary.

:Video Summarization, Support vector machine, Relevance vector machine, Gabor filter,Facial expression

"EFFICIENT VIDEO SUMMARIZATION BASED ON VIDEO EMOTION AND AUDIO SEMANTIC ANALYSIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.42-48, June 2019, Available :http://www.jetir.org/papers/JETIR1906V07.pdf

"EFFICIENT VIDEO SUMMARIZATION BASED ON VIDEO EMOTION AND AUDIO SEMANTIC ANALYSIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp42-48, June 2019, Available at : http://www.jetir.org/papers/JETIR1906V07.pdf