Authors: Chongbo Zhou Chuancai Liu
Publish Date: 2014/02/02
Volume: 74, Issue: 15, Pages: 5623-5634
Abstract
Automatic cosegmentation is a challenging task because it lacks of prior cues In this paper an efficient region contrast based method is proposed for salient object detection and segmentation The coarse location information of the salient object and the background is first estimated based on the distribution of the detected keypoints Histograms of the estimated foreground and background are calculated as their features An image is then oversegmented into superpixels and their histograms are computed The saliency of a superpixel is obtained according to the similarity coefficients between the superpixel and the estimated foreground/background With the saliency map the salient object in the image is extracted using a graph cut based optimized framework The proposed method is compared with stateoftheart methods on the widely used dataset and the experiments show that it overall obtains more accurate results
Keywords: