Foreground and Background Feature Fusion Using a Convex Hull Based Center Prior for Salient Object Detection

Abstract

The human vision system has the ability to detect visual saliency extraordinarily quickly and reliably. In computer vision, visual saliency object detection aims to replicate the mechanism of human visual system in selecting regions of interest from complex scenes. Salient object detection splits the image into two regions, i.e., foreground salient object and background. Different features of the underlying image might be useful for identifying the two regions. In this study, we develop a bottom-up method to detect salient objects using informative features and a convex-hull-based center prior. We explore complementary characteristics of features and develop one effective way to integrate those features. The performance of the new method is compared with seven state-of-the-art methods on three different benchmark datasets. The quantitative (e.g, precision-recall curve, receiver operating characteristic (ROC) curve, and F -measure) and qualitative results indicate the new method improves salient object detection (SOD)performance.