Combination of Dissimilar Feature Scores for Image Quality Assessment Using Particle Swarm Optimization Algorithm

Abstract

In this paper, we propose a new combination technique for full-reference image quality assessment (IQA) by utilizing three better-recognized IQA methods. To select the IQA methods, we first pick up Most Apparent Distortion (MAD) as the most appropriate IQA index for image quality databases and then add two other indices, MS-SSIM and FSIM, which have the most dissimilar features from the first index MAD. The parameter values employed in the new IQA score are optimized using the particle swarm optimization algorithm. By experiments, it is validated that the proposed method gives the best performance for various databases and outperforms the other state-of-the-art methods.