Abstract
Key frame extraction is the main key process in the video content management system to summarize the video and it is easy for the content searchers to find the particular content or particular scene from the given video and also users can easily find summary of the given video without seeing full video. Key frames provides a most desirable abstraction for video indexing, browsing, and retrieval. Key frame extraction process is to represent the full video in terms of short video clips. In this work, key frames are extracted using feature vectors, which are obtained from features calculated for each sub-band in the contour let transform. Where the energy and standard deviation features of each sub-band are used to form a feature vector. The experimental results proved that this novel method had more accuracy rate and low error rate.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call