Screen image quality assessment incorporating structural degradation measurement

Screen content is typically composed of computer generated text and graphics. The contents shown on the screen exhibit various unnatural properties, such as sharp edges and thin lines with few color variations. In this paper we design a novel structure-induced quality metric (SIQM) for assessing the screen image quality. The proposed SIQM works by weighting the benchmark structural similarity index (SSIM) with the structural degradation measurement that is computed using SSIM as well. Experimental results conducted on the newly released subjective quality database concerning screen images show that on one hand the proposed technique is superior to existing quality measures, and on the other hand our model is able to optimize screen video coding and thus introduce remarkable visual quality improvement.

I. Introduction

Recent advances in cloud computing and mobile computing have brought new challenges to the quality assessment community. In many scenarios, e.g. cloud-mobile convergence [1], cloud gaming [2], and remote computing platforms [3], the remote computing is facilitated by users' interaction with the local display interface, which is typically realized by computer generated screen images. Usually, the screen images are generated and compressed at the server, and then transmitted to the thin client side. This process inevitably introduces distortions. The quality of screen images directly determines the interactivity performance and users' experience. Hence accurately predicting the screen quality with an objective model plays a variety of roles in cloud and remote computing applications. First, it can be used to dynamically monitor the screen image quality and adjust resources to improve remote computing experience. Second, it can be used for optimization, e.g. screen content compression to attain better rate distortion performance. Third, it can work as a benchmark in the quality evaluation of the remote computing system.