The key frame extraction algorithm based on the indigenous disturbance variation difference video

Abstract

Abstract In view of the traditional support vector machine (SVM) learning algorithm for widespread learning parameters is not easy determined in the process of video key frame extraction, the problem of low accuracy, an independent perturbation variable difference SVM algorithm used for video key frame extraction. First of all, the study of the biological mechanism of differential evolution algorithm, put forward an improved way of autonomic disturbance variation. Secondly, combined with improved forms of independent disturbance differential evolution algorithm for SVM parameters optimization, designed the key frame extraction algorithm of the video based on the improved differential of SVM algorithm. Through the standard test functions and video test database experiments show that the improvement of autonomic disturbance variation difference video key frame extraction algorithm can more effectively optimize parameters of support vector machine, so as to contribute to the improvement of the recall of video retrieval rate of (quasi) two algorithms performance evaluation standard.