Key frame extraction based on improved frame blocks features and second extraction

An improved key frame extraction algorithm based on the low-level features of image is proposed in this paper. Firstly, each frame is divided into equal area of rectangular ring. Secondly, sub-block accumulative color histogram is extracted as color features and different weight is set for different rectangle rings in order to highlight the central part of frame. Thirdly, key frames are selected according to the significant change of frames. Lastly, the algorithm is optimized and key frames are selected in accordance with the frames of location in the video. The experimental results show that the proposed algorithm has good adaptability and can effectively reduce the redundant key frames when the shot has a sudden flash or the object moves fast.