Unified non-uniform scale adaptive sampling model for quality assessment of natural scene and screen content images

Abstract

Among many multimedia scenarios, digital images are mainly composed of natural scene images (NSIs) and screen content images (SCIs). NSIs are always captured by cameras from the real world while SCIs are typically the mixture of pictures and text. Traditional full-reference image quality assessment (IQA) metrics are designed for natural scene images, and they cannot work well on SCIs, because they do not take account of characteristics of different visual content/regions between NSIs and SCIs. Inspired by early eye movement study that human visual system samples the world non-completely or non-uniformly, we observe that human brain perceive different image content at different scales. Given these discoveries, we propose a non-uniform scale adaptive sampling model (NUSM) which dedicates to preprocess the input images for IQA methods, enabling traditional NSI IQA models to predict the quality of SCIs effectively. The proposed sampling model applies different sample scales into different regions to generate pre-sampled image pairs, then send to existing IQAs to evaluate the quality of images. The experimental results demonstrate that our model has achieved a promising performance on both NSIs and SCIs.