Under natural viewing conditions humans tend to fixate on specific parts of the image that interests them naturally. Understanding the mechanisms of the human visual attention may benefit numerous applications in a various fields of engineering, marketing and art such as image quality evaluation, label design, human computer interaction, etc.Saliency map, proposed by Dirk Walther et al., represents the regions which are more prominent than other regions in terms of low level image properties such as intensity, color and orientation. We propose in this paper to modify this saliency map algorithm to account for one high-level feature, human faces, to better mimic the natural human attention and compare it to gaze maps obtained experimentally. The fixations of the gaze map are compared with the most salient regions of the saliency map. The factors that influence the relationship between the saliency maps and gaze maps are analyzed. Gaze map analysis was done for 20 test subjects using eye tracking device as they were shown a set of 190 images.
Puneet Sharma, Faouzi Alaya Cheikh, Jon Yngve Hardeberg, "Saliency Map for Human Gaze Prediction in Still Images" in Proc. IS&T 16th Color and Imaging Conf., 2008, pp 332 - 337, https://doi.org/10.2352/CIC.2008.16.1.art00063