A correlation method of image quality assessment based on SVM and GA

In this paper, we propose a correlation method to assess image quality based on support vector machine (SVM) and genetic algorithm (GA). Instead of the simple linear function to correlate objective indicators with subjective scores of images, we introduce SVM for the correlation function, make GA as the search algorithm, and finally get the image quality assessment model. The results of experiments show: It is effective to introduce SVM to make correlation between objective indicators and subjective scores for image quality assessment; the correlation between objective indicators and subjective scores is better by using SVM based on GA.