Visual saliency based on natural scene statistics

Abstract

Visual saliency is the perceptual quality that makes some items in visual scenes stand out from their immediate contexts. According to the center-surround hypothesis of saliency, it is commonly assumed that bottom-up saliency is determined by how distinct the stimulus (features) at each location of the visual field is from the stimuli (features) in its surround.Using the center-surround configuration from different scales, we define the saliency measure based on the conditional probability of the center given the surround, which is obtained from natural scene statistics (collected from a large set of images of natural scenes). It is demonstrated that the proposed model of visual saliency predicts well human gaze in free viewing static natural scenes.