Author : Ajay Mushan and Prof. Pujashree Vidap

Video summarization plays important role in too many fields, such as video indexing, video browsing, video compression, video analyzing and so on. One of the fundamental units in the video structure analysis is the key frame extraction, Key frame provide a meaningful frames from the video. Key frame consists meaningful frame from the videos which helps for video summarization. In this proposed model, we present an approach which is based on Convolutional Neural Network, keyframe extraction from videos and static video summarization. First, the video should be converted to frames. Then we perform redundancy elimination techniques to reduce the redundancy from frames. Then extract the keyframes from video by using Convolutional Neural Network (CNN) model. From extracted keyframe we form a video summarization. The results obtained from this proposed model is compare with the VSMM model. The proposed model performed on VSUMM dataset. The results are compared with the VSUMM model duration and video static summary. In    Convolutional Neural Network (CNN) model has trained by using 50 salad datasets to summarize the videos related to cooking video.

Keywords: Video   Summarization, Keyframes, Convolutional Neural Network