Key frame extraction based on Artificial Fish Swarm Algorithm and k-means

Key frame extraction is one of the most important technologies in the content-based video retrieval. In order to extract key frame efficiently from different type of video, an efficient method of key frame extraction based on improved Artificial Fish Swarm Algorithm and k-means was proposed. Firstly, an improved Artificial Fish Swarm Algorithm was applied to the extracted color feature vector to self-organized cluster and obtained an initial clustering result. Secondly, k-means was conducted to optimize the initial clustering result, and a final clustering result was obtained. Finally, the center frame of each clustering was extracted as the key frame. As relevant experiment shows the representative of the key frame extracted by using this algorithm are better than other algorithms and the extracted key frame could adequately express the primary content of the video.