点击次数：

论文类型：期刊论文

论文编号：j.neucom.2016.10.007

发表时间：2017-01-26

发表刊物：Neurocomputing

收录刊物：SCI

所属单位：信息与通信工程学院

刊物所在地：荷兰

学科门类：工学

一级学科：信息与通信工程

卷号：222

页面范围：81-90

ISSN号：0925-2312

关键字：Saliency detection; Joint modeling; Object shape; Local consistency

摘要：Saliency detection is the task of locating informative regions in an image, which is a challenging task incomputer vision. In contrast to the existing saliency detection models that focus on either local or global image
property, an effective salient object detection method is introduced based on joint modeling global shape and local consistency. To this end, Restricted Boltzmann Machine (RBM) is utilized to model salient object shape as
global image property and Conditional Random Field(CRF), on the other hand, is adopted to achieve its local consistency. In order to obtain the final salienc