Self-adaptive scale transform for IQA metric

Recently, an increasing number of image quality assessment (IQA) algorithms have been developed based on multi-scale methods, such as MS-SSIM, IFC, VIF and IW-PSNR/SSIM. Inspired by the achievement of multi-scale type of IQA algorithms, this paper proposes a self-adaptive scale transform based IQA approach. Using image size and viewing distance as input variables, we construct a self-adaptive scale transform function to estimate the suitable scale transform coefficient for the following image quality metrics. Two of the most well-known full-reference IQA methods (PSNR and SSIM), and three publicly-available subjectrated image databases (LIVE, IVC and Toyama-MICT) with clear image size and viewing distance values are used as testing beds in this paper. Experimental results and comparative studies on different combinations of IQA methods and image databases suggest the effectiveness and the robustness of the proposed approach.