Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/22052
Title: Salient object detection using content-sensitive hypergraph representation and partitioning
Authors: Liang, Z
Chi, Z 
Fu, H
Feng, D
Keywords: Discriminant color channel selection
Hypergraph representation
Incremental hypergraph partitioning
Potential Region-Of-Interest (p-ROI) extraction
Salient object detection
Issue Date: 2012
Publisher: Elsevier
Source: Pattern recognition, 2012, v. 45, no. 11, p. 3886-3901 How to cite?
Journal: Pattern recognition 
Abstract: As an important problem in image understanding, salient object detection is essential for image classification, object recognition, as well as image retrieval. In this paper, we propose a new approach to detect salient objects from an image by using content-sensitive hypergraph representation and partitioning. Firstly, a polygonal potential Region-Of-Interest (p-ROI) is extracted through analyzing the edge distribution in an image. Secondly, the image is represented by a content-sensitive hypergraph. Instead of using fixed features and parameters for all the images, we propose a new content-sensitive method for feature selection and hypergraph construction. In this method, the most discriminant color channel which maximizes the difference between p-ROI and the background is selected for each image. Also the number of neighbors in hyperedges is adjusted automatically according to the image content. Finally, an incremental hypergraph partitioning is utilized to generate the candidate regions for the final salient object detection, in which all the candidate regions are evaluated by p-ROI and the best match one will be the selected as final salient object. Our approach has been extensively evaluated on a large benchmark image database. Experimental results show that our approach can not only achieve considerable improvement in terms of commonly adopted performance measures in salient object detection, but also provide more precise object boundaries which is desirable for further image processing and understanding.
URI: http://hdl.handle.net/10397/22052
ISSN: 0031-3203
EISSN: 1873-5142
DOI: 10.1016/j.patcog.2012.04.017
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

21
Last Week
1
Last month
0
Citations as of Dec 9, 2017

WEB OF SCIENCETM
Citations

16
Last Week
0
Last month
0
Citations as of Oct 18, 2017

Page view(s)

40
Last Week
3
Last month
Checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.