DocumentCode :
3404571
Title :
Context-aware saliency detection
Author :
Goferman, Stas ; Zelnik-Manor, Lihi ; Tal, Ayellet
Author_Institution :
Technion - Israel Inst. of Technol., Haifa, Israel
fYear :
2010
fDate :
13-18 June 2010
Firstpage :
2376
Lastpage :
2383
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.
Keywords :
feature extraction; image processing; context-aware saliency detection; detection algorithm; dominant object; fixation points; image regions; image retargeting; psychological literature; Application software; Computer vision; Detection algorithms; Focusing; Humans; Layout; Object detection; Object recognition; Psychology; Springs;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location :
San Francisco, CA
ISSN :
1063-6919
Print_ISBN :
978-1-4244-6984-0
Type :
conf
DOI :
10.1109/CVPR.2010.5539929
Filename :
5539929
Link To Document :
بازگشت