Psychovisual saliency in color images

Abstract

Visual attention is an indispensable component of complex vision tasks. When looking at a complex scene, our ocular perception is confronted with a large amount of data that needs to be broken down for processing by our psychovisual system. Selective visual attention provides a mechanism for serializing the visual data, allowing for sequential processing of the content of the scene. A Bottom-Up computational model is described that simulates the psycho-visual model of saliency based on features of intensity and color. The method gives sequential priorities to objects which other computational models cannot account for. The results demonstrate a fast execution time, full resolution maps and high detection accuracy. The model is applicable on both natural and artificial images.