Abstract

Visual attention is an important issue in image and video analysis and keeps being an open problem in the computer vision field. Motivated by the famous Helmholtz principle, a new approach of visual attention analysis is proposed in this paper based on the low level fea- ture statistics of natural images and the Bayesian framework. Firstly, two priors, i.e., Surrounding Feature Prior (SFP ) and Single Feature Prob- ability Distribution (SFPD ) are learned and integrated by a Bayesian framework to compute the chance of happening (CoH ) of each pixel in an image. Then another prior, i.e., Center Bias Prior (CBP ), is learned and applied to the CoH to compute the saliency map of the image. The experimental results demonstrate that the proposed approach is both effective and efficient by providing more accurate and quick visual atten- tion location. We make three ma jor contributions in this paper: (1) A set of simple but powerful priors, SFP, SFPD and CBP, are presented in an intuitive way; (2) A computational model of CoH based on Bayesian framework is given to integrate SFP and SFPD together; (3) A com- putationally plausible way to obtain the saliency map of natural images based on CoH and CBP.