Salient object detection via region contrast and graph regularization

作     者：Xingming WU Mengnan DU Weihai CHEN Jianhua WANG 

作者机构：School of Automation Science and Electrical Engineering Beihang University 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2016年第59卷第3期

页      面：46-59页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by National Natural Science Foundation of China(Grant Nos.61573048 51475017) Beijing Municipal Natural Science Foundation(Grant No.4142033) International Scientific and Technological Cooperation Projects of China(Grant No.2015DFG12650) 

主　　题：salient object detection region contrast region compactness global distinctness graph regular ization 

摘      要：Detection of salient objects in an image is now gaining increasing research interest in computer vision community. In this study, a novel region-contrast based saliency detection solution involving three phases is proposed. First, a color-based super-pixels segmentation approach is used to decompose the image into regions. Second, three high-level saliency measures which could effectively characterize the salient regions are evaluated and integrated in an effective manner to produce the initial saliency map. Finally, we construct a pairwise graphical model to encourage that adjacent image regions with similar features take continuous saliency values, thus producing the more perceptually consistent saliency map. We extensively evaluate the proposed method on three public benchmark datasets, and show it can produce promising results when compared to 14state-of-the-art salient object detection approaches.