Image quality assessment via spatial structural analysis

Abstract

The human visual system is sensitive to image structural information. Modeling of image structural similarity has been regarded as suitable for achieving perceptual quality predictions. However, most structural similarity-based image quality assessment (IQA) methods focus on spatial contrast without fully considering the spatial structural distribution. Hence, we propose an IQA method that considers both spatial contrast and structural distributions. First, the image gray-scale fluctuation map (GFM) is calculated. Second, the spatial structural information variation matrices (SSVMs) between the GFMs of distorted and pristine images are obtained. Finally, the quality prediction model is trained using support vector regression (SVR). The experimental results show that the proposed method can accurately predict human perceptual image quality. Experiments on the LIVE2 database show that the Spearman rank-order correlation coefficient (SROCC) and linear correlation coefficient (LCC) values exceed 0.85, while the scale or distortion type of the training set changes, which indicates stability.