A reduced-reference quality assessment metric for super-resolution reconstructed images with information gain and texture similarity

Abstract

Super-resolution (SR) image reconstruction has been extensively studied in recent years due to its broad uses in machine vision, medical imaging, remote sensing and monitoring systems. However, evaluating the performance of SR algorithms is still an ongoing problem. A number of image quality metrics have been reported in recent years, however, they are not specifically designed for SR reconstructed images, so they are usually limited when assessing SR images. Here, we propose a reduced-reference image quality assessment (IQA) metric for SR images. First, saliency detection is used on the high-resolution (HR) images, and low-resolution (LR) images are used to generate the corresponding saliency maps. Second, the information gain and texture similarity between the HR images and the LR images are calculated to quantify the image quality degradation. Finally, the information gain and the texture similarity are weighted to predict the quality of SR images. Extensive experiments illustrate that the proposed metric has better performance for SR images than the existing state-of-the-art IQA algorithms.