Key-Frame Extraction Algorithm Based on Entropy

An improved shots clustering key-frame extraction algorithm based on entropy is presented. Using the color information in the video frames, the algorithm looks every frame of a shot as a special sample and selects appropriate feature. And then through the improvement of the clustering analysis of video sequences to acquire the center value of various classes and the membership degree of every sample relative to the classes, finally the shots will be divided into several sub-shots. According to the relatively uniform of the contents in the sub-shots and the large differences between different classes, as well as the value of the maximum image entropy corresponds to the maximum amount of information in the information theory, the value of maximum entropy frame is extracted as the key-frame from each class. The method overcomes the shortcomings of the traditional key-frame extraction methods that the numbers of the key-frame are fixed. Experiments based on various videos show that the algorithm is more reasonable.