The Key Frame Extraction Algorithm Based on the Indigenous Disturbance Variation Difference Video

ABSTRACT

In view of the traditional support vector machine (SVM) learning algorithm’s learning parameters are not easily determined in the process of video key frame extraction and the accuracy is low. An independent perturbation variable difference SVM algorithm is used for video key frame extraction. First of all, the biological mechanism of differential evolution algorithm was analyzed, and then an improved way of autonomic disturbance variation was put forward. Secondly, combined with improved forms of independent disturbance differential evolution algorithm for SVM parameters optimization, the key frame extraction algorithm of the video based on the improved differential of SVM algorithm was designed. The standard test functions and video test database experiment show that the improvement of autonomic disturbance variation difference video key frame extraction algorithm can optimize parameters of support vector machine more effectively and contribute to the improvement of video retrieval.

Keywords: