Graph-Based Salient Region Detection through Linear Neighborhoods
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 tack...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2016-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2016/8740593 |
id |
doaj-7113a1254f934e60856c5a4be87ffa05 |
---|---|
record_format |
Article |
spelling |
doaj-7113a1254f934e60856c5a4be87ffa052020-11-25T00:42:38ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472016-01-01201610.1155/2016/87405938740593Graph-Based Salient Region Detection through Linear NeighborhoodsLijuan Xu0Fan Wang1Yan Yang2Xiaopeng Hu3Yuanyuan Sun4School of Computer Science and Technology, Dalian University of Technology, No. 2 Linggong Road, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, No. 2 Linggong Road, Dalian 116024, ChinaSchool of Computer and Information Technology, Liaoning Normal University, No. 850 Huanghe Road, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, No. 2 Linggong Road, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, No. 2 Linggong Road, Dalian 116024, ChinaPairwise 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.http://dx.doi.org/10.1155/2016/8740593 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lijuan Xu Fan Wang Yan Yang Xiaopeng Hu Yuanyuan Sun |
spellingShingle |
Lijuan Xu Fan Wang Yan Yang Xiaopeng Hu Yuanyuan Sun Graph-Based Salient Region Detection through Linear Neighborhoods Mathematical Problems in Engineering |
author_facet |
Lijuan Xu Fan Wang Yan Yang Xiaopeng Hu Yuanyuan Sun |
author_sort |
Lijuan Xu |
title |
Graph-Based Salient Region Detection through Linear Neighborhoods |
title_short |
Graph-Based Salient Region Detection through Linear Neighborhoods |
title_full |
Graph-Based Salient Region Detection through Linear Neighborhoods |
title_fullStr |
Graph-Based Salient Region Detection through Linear Neighborhoods |
title_full_unstemmed |
Graph-Based Salient Region Detection through Linear Neighborhoods |
title_sort |
graph-based salient region detection through linear neighborhoods |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1024-123X 1563-5147 |
publishDate |
2016-01-01 |
description |
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. |
url |
http://dx.doi.org/10.1155/2016/8740593 |
work_keys_str_mv |
AT lijuanxu graphbasedsalientregiondetectionthroughlinearneighborhoods AT fanwang graphbasedsalientregiondetectionthroughlinearneighborhoods AT yanyang graphbasedsalientregiondetectionthroughlinearneighborhoods AT xiaopenghu graphbasedsalientregiondetectionthroughlinearneighborhoods AT yuanyuansun graphbasedsalientregiondetectionthroughlinearneighborhoods |
_version_ |
1725281269887008768 |