Visual Attention and Visual Quality

Computational saliency in image quality assessment
We performed an exhaustive statistical evaluation to assess the added value of computational saliency in objective image quality assessment. The study includes 20 state-of-the-art saliency models and 12 best-known image quality metrics (IQMs).

W. Zhang, A. Borji, Z. Wang, P. Le Callet and H. Liu, "The Application of Visual Saliency Models in Objective Image Quality Assessment: A Statistical Evaluation," in IEEE Transactions on Neural Networks and Learning Systems, vol. 27, no. 6, pp. 1266-1278, June 2016.

Paper PDF
Download CSIQA

A reliable collection of eye-tracking data for image quality research
We developed a new experimental methodology to obtain reliable eye-tracking data for image quality research. The study includes 160 human observers freely viewing 288 images of varying quality, and provides insights into the optimal use of visual attention in image quality assessment.

W. Zhang and H. Liu, "Towards A Reliable Collection of Eye-tracking Data for Image Quality Research: Challenges, Solutions and Applications," in IEEE Transactions on Image Processing.

Paper PDF
Download SIQ288

A reliable collection of eye-tracking data for video quality research
We performed a large-scale eye-tracking experiment that involved 160 human observers and 160 video stimuli distorted with different distortion types at various degradation levels. We assessed the capabilities of saliency in improving the performance of video quality metrics (VQMs).

W. Zhang and H. Liu, "Study of Saliency in Objective Video Quality Assessment," in IEEE Transactions on Image Processing, vol. 26, no. 3, pp. 1275-1288, March 2017.

Paper PDF
Download SVQ160

Wei Zhang and Dr Hantao Liu (
School of Computer Science and Informatics
Cardiff University
United Kingdom