Selection of Key Frames Through the Analysis and Calculation of the Absolute Difference of Histograms

Video has a wide range of applications, such as industry, education, health, etc. Carrying out important studies and research in this field, the processing of images and video is a subject currently under study. It is still a challenge for its degree of complexity. Different methodologies for video processing have been proposed and applied in the last decades. One of the most commonly used method is the extraction of the key frames to compress the video data. In this paper, we propose a simple low-complexity method, which can select key frames through the analysis and calculation of the absolute difference of histograms of consecutive frames from video data. Using a short video, we first determine the number of frames of this video. Second, the mean and standard deviation of the absolute difference between two consecutive frame and previously equalized frames is calculated to improve the contrasts levels of the image. Then an appropriate value of the threshold is set and a comparison is established, wherein if the absolute difference is greater than the threshold, the current frame is selected as the key frame. The results show that the algorithm not only presents a low level of complexity, but also is efficient since the effort needed for subsequent work with these key frames is quite low.