A novel optimization framework for salient object detection

作者：Zhang, Hanling; Xu, Min^*; Zhuo, Liyuan; Havyarimana, Vincent

来源：Visual Computer, 2016, 32(1): 31-41.

DOI：10.1007/s00371-014-1053-z

• Visual saliency
• Boundary contrast
• Smoothness prior
• Optimization framework

Visual saliency aims to locate the noticeable regions or objects in an image. In this paper, a coarse-to-fine measure is developed to model visual saliency. In the proposed approach, we firstly use the contrast and center bias to generate an initial prior map. Then, we weight the initial prior map with boundary contrast to obtain the coarse saliency map. Finally, a novel optimization framework that combines the coarse saliency map, the boundary contrast and the smoothness prior is introduced with the intention of refining the map. Experiments on three public datasets demonstrate the effectiveness of the proposed method.

• 出版日期2016-1
• 单位湖南大学