Saliency Extraction for Gaze-Contingent Displays

Organic Computing is beginning to provide computer systems with organic and biological properties. We believe these systems will benefit from user interfaces that integrate the user more tightly with the system and optimize the way the user absorbs information. To this end, we propose gaze-contingent interactive displays that monitor and guide the user's gaze to make interaction with the system more effective and enjoyable. A vital prerequisite for such a system is the ability to predict one or several salient locations that the user is likely to attend to in a dynamic display, with the goal of then modifying the display to influence the user's direction of gaze. In this paper, we present a structure-tensor-based saliency measure and a novel algorithm for extracting salient locations from saliency maps by using the mechanism of selective lateral inhibition. We assess the quality of the extracted locations by comparing them to the locations actually attended by test subjects.