Context-Aware Saliency Detection
Context-Aware Saliency Detection
复制标题
DOI：
10.1109/tpami.2011.272
复制
发表时间：
2012-10-01
影响因子：
23.6
通讯作者：
Tal, Ayellet
中科院分区：
文献类型：
--
作者：
Goferman, Stas;Zelnik-Manor, Lihi;Tal, Ayellet
我们提出了一种新类型的显着性上下文感知显着性，其目的是检测代表场景的图像区域。该定义不同于先前的定义，其目标是识别注视点或检测主要对象。根据我们的显着性定义，我们提出了一个检测算法，这是基于四个原则观察到的心理学文献。所提出的方法的好处进行评估，在两个应用程序中，占主导地位的对象的上下文是一样重要的对象本身。在图像重定向中，我们证明了使用显着性可以防止重要区域的扭曲。在总结中，我们表明，我们的显着性有助于产生紧凑，吸引人，和翔实的摘要。
We propose a new type of saliency-context-aware saliency-which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, we present a detection algorithm which is based on four principles observed in the psychological literature. The benefits of the proposed approach are evaluated in two applications where the context of the dominant objects is just as essential as the objects themselves. In image retargeting, we demonstrate that using our saliency prevents distortions in the important regions. In summarization, we show that our saliency helps to produce compact, appealing, and informative summaries.