Key Frame Extraction Based on Connectivity Clustering

Key frames play a very important role in video retrieval. In this paper, we introduce a novel method to extract key frames to represent video shot based on connectivity clustering. Compared with other methods, the proposed method can dynamically divide the frames into clusters depending on the content of shot, and then the frame closest to the cluster centroid is chosen as the key frame for the video shot. Experimental results and the comparisons with other methods on various types of video sequences illustrate the high performance of the proposed method.