Global Contrast Based Salient Region Detection

Cheng, Ming‐Ming; Mitra, Niloy J.; Huang, Xiaolei; Torr, Philip H. S.; Hu, Shi‐Min

doi:10.1109/tpami.2014.2345401

articleIEEE Transactions on Pattern Analysis and Machine IntelligenceAug 5, 2014Closed access

Global Contrast Based Salient Region Detection

MCMing‐Ming Cheng NJNiloy J. Mitra XHXiaolei Huang PHPhilip H. S. Torr SHShi‐Min Hu

Nankai University · University College London · +3 more institutions

Indexed incrossref

Abstract

Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object detection algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut, namely SaliencyCut, for high quality unsupervised salient object segmentation. We extensively evaluated our…

Citation impact

2,440

total citations

FWCI: 138.40
Percentile: 100%
References: 98

Citations per year

Authors

5

Topics & keywords

Topics

Keywords

Artificial intelligence
Computer science
Salient
Contrast (vision)
Pattern recognition (psychology)
Computer vision
Image retrieval
Segmentation

No related works found for this paper.