Gaze-Centric Image Analysis for Efficient Visual Search

Despite recent advances in computer vision, pattern recognition, and image processing, many visual tasks remain unsolved. Consider, for example, visual search – the problem of finding a target in a background of distracters. Whenever we look for a familiar face in an audience, or search for a misplaced item, we engage in visual search. Given the infinite variations of a target’s features (size, orientation, color), and background conditions (lighting, occlusion), it is a marvel that humans excel at searching and distinguishing objects. One aspect of the human visual system (HVS) critical to its success as an efficient searcher is its active nature of looking. To avoid the data glut accompanying its large field of view, the HVS processes only a tiny central region at high resolution, while the resolution of processing falls rapidly towards the periphery. To assimilate visual information from this foveated input (Fig. 1), the HVS uses a combination of steady eye fixations linked by rapid ballistic eye movements called saccades (Fig. 2). Fig 1: Foveated image when fixating the climber