Graph-Based Salient Region Detection through Linear Neighborhoods
Joint Authors
Hu, Xiao Peng
Xu, Lijuan
Yang, Yan
Wang, Fan
Yuanyuan, Sun
Source
Mathematical Problems in Engineering
Issue
Vol. 2016, Issue 2016 (31 Dec. 2016), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2016-05-31
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
Pairwise neighboring relationships estimated by Gaussian weight function have been extensively adopted in the graph-based salient region detection methods recently.
However, the learning of the parameters remains a problem as nonoptimal models will affect the detection results significantly.
To tackle this challenge, we first apply the adjacent information provided by all neighbors of each node to construct the undirected weight graph, based on the assumption that every node can be optimally reconstructed by a linear combination of its neighbors.
Then, the saliency detection is modeled as the process of graph labelling by learning from partially selected seeds (labeled data) in the graph.
The promising experimental results presented on some datasets demonstrate the effectiveness and reliability of our proposed graph-based saliency detection method through linear neighborhoods.
American Psychological Association (APA)
Xu, Lijuan& Wang, Fan& Yang, Yan& Hu, Xiao Peng& Yuanyuan, Sun. 2016. Graph-Based Salient Region Detection through Linear Neighborhoods. Mathematical Problems in Engineering،Vol. 2016, no. 2016, pp.1-11.
https://search.emarefa.net/detail/BIM-1112758
Modern Language Association (MLA)
Xu, Lijuan…[et al.]. Graph-Based Salient Region Detection through Linear Neighborhoods. Mathematical Problems in Engineering No. 2016 (2016), pp.1-11.
https://search.emarefa.net/detail/BIM-1112758
American Medical Association (AMA)
Xu, Lijuan& Wang, Fan& Yang, Yan& Hu, Xiao Peng& Yuanyuan, Sun. Graph-Based Salient Region Detection through Linear Neighborhoods. Mathematical Problems in Engineering. 2016. Vol. 2016, no. 2016, pp.1-11.
https://search.emarefa.net/detail/BIM-1112758
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1112758