SVM Visual Classification Based on Weighted Feature of Genetic Algorithm

In order to enhance the accuracy rate of video classification, this article proposes a support SVM classification of using genetic algorithm to optimize features weighting (GA-SVM). First, this article extracts the colors and textural features of video, then adopts improved genetic algorithm to determine features weighting, and at last uses support SVM to establish video classifier and implements simulation test of corel video database. The results show that comparing with other video category algorithm, GA-SVM enhances accuracy of video classification.