Salient region detection via locally smoothed label propagation: With application to attention driven image abstraction
Salient region detection via locally smoothed label propagation: With application to attention driven image abstraction
复制标题
DOI：
10.1016/j.neucom.2016.12.028
复制
发表时间：
2017-03
期刊：
影响因子：
6
通讯作者：
Hong Li;E. Wu;Wen Wu
中科院分区：
文献类型：
--
作者：
Hong Li;E. Wu;Wen Wu
背景先验和标签传播被广泛提倡用于显著区域检测。然而，传统的基于背景先验的模型假设图像边界上的所有或部分像素是背景。而基于标签传播的模型在优化时只考虑了两两光滑性。为了解决这两个缺点，我们提出了一个框架，利用背景先验和标签传播来生成更可靠的显着性图。首先，提出了一种新的最优种子估计策略，自适应和鲁棒地从细化的背景图和前景先验中选择信息量最大的种子。然后，提出了一种新的标签传播模型，该模型同时考虑了成对和局部平滑约束，根据估计的背景和前景种子来学习显著性得分。最后，我们提出了一种新的显著区域检测应用--注意驱动的图像提取。在三个广泛使用的数据集上的定量和定性评价都证明了所提出的方法优于其他几个国家的最先进的方法。
Background prior and label propagation have been widely advocated for salient region detection. However, traditional background prior based models heuristically assume that all or parts of the pixels on the image boundary are background. And the label propagation based models only consider the pairwise smoothness in optimization. To tackle these two shortcomings, we propose a framework which utilizes background prior and label propagation to generate more reliable saliency maps. Firstly, a novel optimal seeds estimation strategy is proposed to adaptively and robustly choose the most informative seeds from refined background map and foreground prior. Then, a new label propagation model which takes into account both the pairwise and local smoothness constraint is proposed to learn the saliency score according to the estimated background and foreground seeds. Last but not least, we present a new application of salient region detection named attention driven image abstraction. Both quantitative and qualitative evaluations on three widely used datasets demonstrate the superiority of the proposed method to other several state-of-the-art methods.