Contextual Hypergraph Modeling for Salient Object Detection

Salient object detection aims to locate objects that capture human attention within images. Previous approaches often pose this as a problem of image contrast analysis. In this work, we model an image as a hyper graph that utilizes a set of hyper edges to capture the contextual properties of image pixels or regions. As a result, the problem of salient object detection becomes one of finding salient vertices and hyper edges in the hyper graph. The main advantage of hyper graph modeling is that it takes into account each pixel's (or region's) affinity with its neighborhood as well as its separation from image background. Furthermore, we propose an alternative approach based on center-versus-surround contextual contrast analysis, which performs salient object detection by optimizing a cost-sensitive support vector machine (SVM) objective function. Experimental results on four challenging datasets demonstrate the effectiveness of the proposed approaches against the state-of-the-art approaches to salient object detection.

1. Introduction

Image saliency detection aims to effectively identify important and informative regions in images. Early approaches in this area focus mainly on predicting where humans look, and thus work only on human eye fixation data [1]–[3]. Recently, a large body of work concentrates on salient object detection [4]–[17], whose goal is to discover the most salient and attention-grabbing object in an image. This has a wide range of applications such as image retargeting [18], image classification [19], and image segmentation [20], [21]. Because it is difficult to define saliency analytically, the performance of salient object detection is evaluated on datasets containing human-labeled bounding boxes or foreground masks.