Issue No. 10 - Oct. (2012 vol. 34)
Ayellet Tal , Israel Institute of Technology, Haifa
Lihi Zelnik-Manor , Israel Institute of Technology, Haifa
Stas Goferman , Israel Institute of Technology, Haifa
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.
Feature extraction, Context awareness, Visualization, Object recognition, Estimation, Image color analysis, Human factors, context aware., Image saliency, visual saliency
Ayellet Tal, Lihi Zelnik-Manor, Stas Goferman, "Context-Aware Saliency Detection", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1915-1926, Oct. 2012, doi:10.1109/TPAMI.2011.272