Screen content image (SCI) has recently emerged as an active topic due to the rapidly increasing demand in many graphically rich services such as wireless displays and virtual desktops. SCIs are often composed of pictorial regions and computer generated textual/graphical content, which exhibit different statistical properties that often lead to different viewer behaviors. Inspired by this, we propose an objective quality assessment approach for SCIs that incorporates both visual field adaptation and information content weighting into structural similarity based local quality assessment. Furthermore, we develop a perceptual screen content coding scheme based on the newly proposed quality assessment measure, targeting at further improving the SCI compression performance. Experimental results show that the proposed quality assessment method not only better predicts the perceptual quality of SCIs, but also demonstrates great potentials in the design of perceptually optimal SCI compression schemes.

+More

content image sci computer generated textualgraphical content statistical properties pictorial regions virtual desktops structural similarity based local quality assessment visual field adaptation perceptual screen content coding scheme wireless displays perceptual quality of scis perceptually optimal sci compression schemes information content weighting

Zhou Wang, Weisi Lin, Ke Gu,Shiqi Wang, Kai Zeng,.Objective Quality Assessment and Perceptual Compression of Screen Content Images. 38 (1),47-58.

Zhou Wang, et al."Objective Quality Assessment and Perceptual Compression of Screen Content Images" 38

Zhou Wang, Weisi Lin, Ke Gu,Shiqi Wang, Kai Zeng,"Objective Quality Assessment and Perceptual Compression of Screen Content Images"