Multiscale phase congruency analysis for image edge visual saliency detection

A novel multiscale phase congruency (MPC) based analysis method is proposed in this paper for edge saliency detection and non-salient region texture suppression. Several MPC maps are proposed to be merged. Gaussian function based center priors and threshold processing are applied for the final edge saliency map generation, which can effectively suppress the textures and the detailed edges of non-salient regions. Experimental results show that the proposed MPC based edge saliency detection method can better generate edge saliency map for the most salient region in an image than the traditional PC based edge detection method and the other state-of-the-art saliency detection methods.