Key frame extraction based on improved hierarchical clustering algorithm

Key frame greatly reduces the amount of data required in video indexing and provides a suitable abstract for video browsing and retrieval. Key frame extraction plays an important role in content-based video stream analysis, retrieval and inquiry. In order to extract key frame efficiently from different type of videos, in this paper we propose an improved hierarchical clustering algorithm that combing K-means algorithm. The improved hierarchical clustering algorithm is used to obtain an initial clustering result. And K-means is conducted to optimize the initial clustering result and obtain the final clustering result. Finally, the center frame of each clustering is extracted as key frame. Experimental results show that compared with other existing methods, the representations of key frame extracted by our algorithm are better in expressing the primary content of video.