Learning Saliency by MRF and Differential Threshold
Learning Saliency by MRF and Differential Threshold
复制标题
DOI：
10.1109/tsmcb.2013.2238927
复制
发表时间：
2013-12
影响因子：
11.8
通讯作者：
Guokang Zhu;Qi Wang;Yuan Yuan-Yuan;Pingkun Yan
中科院分区：
文献类型：
--
作者：
Guokang Zhu;Qi Wang;Yuan Yuan-Yuan;Pingkun Yan
近年来，显着性检测一直是一个引人注目的话题。显著性的可靠检测可以帮助许多有用的处理，而无需先验知识的场景，如内容感知的图像压缩，分割等，虽然已经花了很多的努力，在这方面的主题，特征表达和模型的构建还远远不够完善。因此，所获得的显着性图是不够令人满意的。为了克服这些挑战，本文提出了一种新的基于差分阈值的心理视觉特征，并将其应用于监督马尔可夫随机场框架。在两个公开数据集和一个图像重定向应用上的实验证明了该方法的有效性、鲁棒性和实用性。
Saliency detection has been an attractive topic in recent years. The reliable detection of saliency can help a lot of useful processing without prior knowledge about the scene, such as content-aware image compression, segmentation, etc. Although many efforts have been spent in this subject, the feature expression and model construction are far from perfect. The obtained saliency maps are therefore not satisfying enough. In order to overcome these challenges, this paper presents a new psychologic visual feature based on differential threshold and applies it in a supervised Markov-random-field framework. Experiments on two public data sets and an image retargeting application demonstrate the effectiveness, robustness, and practicability of the proposed method.