| Literature DB >> 22201056 |
Stas Goferman1, Lihi Zelnik-Manor, Ayellet Tal.
Abstract
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.Mesh:
Year: 2012 PMID: 22201056 DOI: 10.1109/TPAMI.2011.272
Source DB: PubMed Journal: IEEE Trans Pattern Anal Mach Intell ISSN: 0098-5589 Impact factor: 6.226