A novel optimization framework for salient object detection
A novel optimization framework for salient object detection
复制标题
DOI：
10.1007/s00371-014-1053-z
复制
发表时间：
2014-11
期刊：
影响因子：
--
通讯作者：
Hanling Zhang;Min Xu;Liyuan Zhuo;Vincent Havyarimana
中科院分区：
文献类型：
--
作者：
Hanling Zhang;Min Xu;Liyuan Zhuo;Vincent Havyarimana
视觉显著性旨在定位图像中值得注意的区域或物体。本文提出了一种从粗到精的方法来模拟视觉显著性。在该方法中，我们首先使用对比度和中心偏差来生成初始先验映射。然后，我们将初始先验图与边界对比度加权，得到粗糙显著性图。最后，提出了一种结合粗糙显著性图、边界对比和平滑先验的优化框架，对粗糙显著性图进行细化。在三个公共数据集上的实验证明了该方法的有效性。
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.