A comparative study of image quality assessment

Image quality assessment (IQA) plays an important role in many image processing tasks. Although several IQA methods have been developed for decades, each matric has its individual characteristic for evaluation. In this paper, we compare popular IQA methods including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean structural similarity index (MSSIM) and feature similarity index (FSIM) on validating 3 different test images with various image degradation factors. The results of comparative experiment show that although each method has different sensitivity for different distortion, MSSIM is a good metric among them in overall performance. It can be used for a wide variety of image degradation. The parameters can be adjusted for different purposes.