4.8 Article

Global Contrast Based Salient Region Detection

Publisher

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2014.2345401

Keywords

Salient object detection; visual attention; saliency map; unsupervised segmentation; image retrieval

Funding

  1. 973 Program [2011CB302205]
  2. NSFC [61120106007, 61133008]
  3. 863 Program [2012AA011802]
  4. Research program of Beijing Education council
  5. EPSRC
  6. Leverhulme Trust
  7. ERC [2012-AdG 321162-HELIOS]
  8. ERC Starting Grant SmartGeometry

Ask authors/readers for more resources

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 algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms 15 existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available