Saliency detection via graph-based manifold ranking

Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan, Ming Hsuan Yang

Research output: Contribution to journalConference article

1135 Citations (Scopus)

Abstract

Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way. We rank the similarity of the image elements (pixels or regions) with foreground cues or background cues via graph-based manifold ranking. The saliency of the image elements is defined based on their relevances to the given seeds or queries. We represent the image as a close-loop graph with super pixels as nodes. These nodes are ranked based on the similarity to background and foreground queries, based on affinity matrices. Saliency detection is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. Experimental results on two large benchmark databases demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy and speed. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field.

Original languageEnglish
Article number6619251
Pages (from-to)3166-3173
Number of pages8
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
Publication statusPublished - 2013 Nov 15
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: 2013 Jun 232013 Jun 28

Fingerprint

Pixels
Seed

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{f07d35ba4fcb473a924157505d7196f6,
title = "Saliency detection via graph-based manifold ranking",
abstract = "Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way. We rank the similarity of the image elements (pixels or regions) with foreground cues or background cues via graph-based manifold ranking. The saliency of the image elements is defined based on their relevances to the given seeds or queries. We represent the image as a close-loop graph with super pixels as nodes. These nodes are ranked based on the similarity to background and foreground queries, based on affinity matrices. Saliency detection is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. Experimental results on two large benchmark databases demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy and speed. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field.",
author = "Chuan Yang and Lihe Zhang and Huchuan Lu and Xiang Ruan and Yang, {Ming Hsuan}",
year = "2013",
month = "11",
day = "15",
doi = "10.1109/CVPR.2013.407",
language = "English",
pages = "3166--3173",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

Saliency detection via graph-based manifold ranking. / Yang, Chuan; Zhang, Lihe; Lu, Huchuan; Ruan, Xiang; Yang, Ming Hsuan.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 15.11.2013, p. 3166-3173.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Saliency detection via graph-based manifold ranking

AU - Yang, Chuan

AU - Zhang, Lihe

AU - Lu, Huchuan

AU - Ruan, Xiang

AU - Yang, Ming Hsuan

PY - 2013/11/15

Y1 - 2013/11/15

N2 - Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way. We rank the similarity of the image elements (pixels or regions) with foreground cues or background cues via graph-based manifold ranking. The saliency of the image elements is defined based on their relevances to the given seeds or queries. We represent the image as a close-loop graph with super pixels as nodes. These nodes are ranked based on the similarity to background and foreground queries, based on affinity matrices. Saliency detection is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. Experimental results on two large benchmark databases demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy and speed. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field.

AB - Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way. We rank the similarity of the image elements (pixels or regions) with foreground cues or background cues via graph-based manifold ranking. The saliency of the image elements is defined based on their relevances to the given seeds or queries. We represent the image as a close-loop graph with super pixels as nodes. These nodes are ranked based on the similarity to background and foreground queries, based on affinity matrices. Saliency detection is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. Experimental results on two large benchmark databases demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy and speed. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field.

UR - http://www.scopus.com/inward/record.url?scp=84887357058&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887357058&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.407

DO - 10.1109/CVPR.2013.407

M3 - Conference article

AN - SCOPUS:84887357058

SP - 3166

EP - 3173

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

M1 - 6619251

ER -