Saliency detection via joint modeling global shape and local consistency

详细信息    查看全文

• 作者：Jinqing Qi ; ^{jinqing@dlut.edu.cn}Author Vitae ; Shijing DongAuthor Vitae ; Fang HuangAuthor Vitae ; Huchuan LuAuthor Vitae
• 关键词：Saliency detection ; Joint modeling ; Object shape ; Local consistency
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：26 January 2017
• 年：2017
• 卷：222
• 期：Complete
• 页码：81-90
• 全文大小：1454 K
• 卷排序：222

文摘

Saliency detection is the task of locating informative regions in an image, which is a challenging task in computer 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 saliency map, a universal framework is introduced to combine the results of RBM and CRF. Experimental results on five benchmark datasets demonstrate that the proposed saliency detection method performs favorably against the existing state-of-the-art algorithms.