Measuring image quality is a complex process that often requires elements of subjective analysis in order to be reliable when the final judge is a human observer. Preference studies show that slight variations in colour have drastically different outcomes in quality perception depending on where they occur. A few ΔE of difference in the colour of a wall may be unnoticed, while a shift of a single ΔE on a face will have a major impact. The perceived quality of images does not in general depend on the image as a whole, but on a few salient regions within. Measuring saliency in images is essential to identify which parts of an image are of particular importance to human observers for subsequent processing. Consequently, a number of algorithms have been developed, that purport to automatically predict an image's salient regions.Most saliency algorithms are based on low-level cues, be it the physiology of the human visual system or image statistics, and are designed with a broad scope in mind. However, studies of human attention and eye movements show that visual attention maps vary significantly depending on the task, due to the influence of high-level cognitive processes.Identifying important regions for perceptual image quality measurement being a critical task, we devise an experimental framework to obtain visual attention maps and compare these to the saliency maps predicted by state-of-the-art algorithms. Measures of correlation and precision-recall curves indicate that automatic saliency measurement is not much better than random, and far from the performance of observers, perhaps suggesting that image quality assessment has more to do with high-level cognitive processes than with low-level vision.
Clément Fredembach, Jue Wang, Geoff J. Woolfe, "Saliency, Visual Attention and Image Quality" in Proc. IS&T 18th Color and Imaging Conf., 2010, pp 128 - 133, https://doi.org/10.2352/CIC.2010.18.1.art00023