000135217 001__ 135217
000135217 005__ 20180913055140.0
000135217 0247_ $$2doi$$a10.1109/CVPR.2009.5206596
000135217 02470 $$2ISI$$a000279038001014
000135217 037__ $$aCONF
000135217 245__ $$aFrequency-tuned Salient Region Detection
000135217 269__ $$a2009
000135217 260__ $$c2009
000135217 336__ $$aConference Papers
000135217 500__ $$aFor code and supplementary material, click on the url below.
000135217 520__ $$aDetection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. These boundaries are preserved by retaining substantially more frequency content from the original image than other existing techniques. Our method exploits features of color and luminance, is simple to implement, and is computationally efficient. We compare our algorithm to five state-of-the-art salient region detection methods with a frequency domain analysis, ground truth, and a salient object segmentation application. Our method outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.
000135217 6531_ $$aIVRG
000135217 6531_ $$aNCCR-MICS
000135217 6531_ $$aNCCR-MICS/CL4
000135217 6531_ $$aK-Space
000135217 6531_ $$aPHAROS
000135217 6531_ $$aSaliency
000135217 6531_ $$aSegmentation
000135217 6531_ $$aFrequency-domain analysis
000135217 6531_ $$avisually salient regions
000135217 700__ $$0242495$$aAchanta, Radhakrishna$$g172126
000135217 700__ $$aHemami, Sheila
000135217 700__ $$aEstrada, Francisco
000135217 700__ $$0241946$$aSüsstrunk, Sabine$$g125681
000135217 7112_ $$aIEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2009)$$cMiami Beach, Florida$$dJune 20-25, 2009
000135217 773__ $$q1597 - 1604$$tIEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2009)
000135217 8564_ $$uhttp://ivrg.epfl.ch/supplementary_material/RK_CVPR09/index.html$$zURL
000135217 8564_ $$s1831586$$uhttps://infoscience.epfl.ch/record/135217/files/1708.pdf$$zn/a
000135217 909C0 $$0252320$$pIVRL$$xU10429
000135217 909CO $$ooai:infoscience.tind.io:135217$$pconf$$pIC
000135217 917Z8 $$x114218
000135217 917Z8 $$x125681
000135217 917Z8 $$x125681
000135217 917Z8 $$x125681
000135217 937__ $$aLCAV-CONF-2009-012
000135217 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000135217 980__ $$aCONF