Global contrast based salient region detection

Handle URI:
http://hdl.handle.net/10754/622089
Title:
Global contrast based salient region detection
Authors:
Cheng, Ming-Ming; Zhang, Guo-Xin; Mitra, Niloy J. ( 0000-0002-2597-0914 ) ; Huang, Xiaolei; Hu, Shi-Min
Abstract:
Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Cheng M-M, Zhang G-X, Mitra NJ, Huang X, Hu S-M (2011) Global contrast based salient region detection. CVPR 2011. Available: http://dx.doi.org/10.1109/CVPR.2011.5995344.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
CVPR 2011
Issue Date:
25-Aug-2011
DOI:
10.1109/CVPR.2011.5995344
Type:
Conference Paper
Sponsors:
This research was supported by the 973 Program (2011CB302205), the 863 Program (2009AA01Z327), the Key Project of S&T (2011ZX01042-001-002), and NSFC (U0735001). Ming-Ming Cheng was funded by Google PhD fellowship, IBM PhD fellowship, and New PhD Researcher Award (Ministry of Edu., CN).
Additional Links:
http://ieeexplore.ieee.org/document/5995344/
Appears in Collections:
Conference Papers; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorCheng, Ming-Mingen
dc.contributor.authorZhang, Guo-Xinen
dc.contributor.authorMitra, Niloy J.en
dc.contributor.authorHuang, Xiaoleien
dc.contributor.authorHu, Shi-Minen
dc.date.accessioned2016-12-29T13:20:20Z-
dc.date.available2016-12-29T13:20:20Z-
dc.date.issued2011-08-25en
dc.identifier.citationCheng M-M, Zhang G-X, Mitra NJ, Huang X, Hu S-M (2011) Global contrast based salient region detection. CVPR 2011. Available: http://dx.doi.org/10.1109/CVPR.2011.5995344.en
dc.identifier.doi10.1109/CVPR.2011.5995344en
dc.identifier.urihttp://hdl.handle.net/10754/622089-
dc.description.abstractReliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.en
dc.description.sponsorshipThis research was supported by the 973 Program (2011CB302205), the 863 Program (2009AA01Z327), the Key Project of S&T (2011ZX01042-001-002), and NSFC (U0735001). Ming-Ming Cheng was funded by Google PhD fellowship, IBM PhD fellowship, and New PhD Researcher Award (Ministry of Edu., CN).en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/document/5995344/en
dc.rights(c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.subjectcomputer visionen
dc.subjectfeature extractionen
dc.subjectimage resolutionen
dc.subjectimage segmentationen
dc.subjectobject recognitionen
dc.subjectHistogramsen
dc.subjectHumansen
dc.subjectImage color analysisen
dc.subjectImage segmentationen
dc.subjectQuantizationen
dc.subjectSmoothing methodsen
dc.subjectVisualizationen
dc.titleGlobal contrast based salient region detectionen
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalCVPR 2011en
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionTNList, Tsinghua University, Chinaen
dc.contributor.institutionLehigh University, United Statesen
kaust.authorMitra, Niloy J.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.