Please use this identifier to cite or link to this item:
PIRA download icon_1.1View/Download Full Text
Title: Hypergraph-based saliency map generation with potential region-of-interest approximation and validation
Authors: Liang, Z
Fu, H
Chi, ZG 
Feng, DD
Issue Date: Jan-2012
Source: Journal of electronic imaging, Jan. 2012, v. 21, no. 1, 013012, p. 1-4
Abstract: A novel saliency model is proposed in this paper to automatically process images in the similar way as the human visual system which focuses on conspicuous regions that catch human beings’ attention. The model combines a hypergraph representation and a partitioning process with potential region-of-interest (p-ROI) approximation and validation. Experimental results demonstrate that the proposed method shows considerable improvement in the performance of saliency map generation.
Keywords: Approximation theory
Graph theory
Image representation
Publisher: SPIE-International Society for Optical Engineering
Journal: Journal of electronic imaging 
ISSN: 1017-9909
EISSN: 1560-229X
DOI: 10.1117/1.JEI.21.1.013012
Rights: Liang Z, Fu H, Chi Z and Feng D, "Hypergraph-based saliency map generation with potential region-of-interest approximation and validation," J. Electron. Imaging., 21(1), 013012, p. 1-4 (2012)
Copyright 2012 Society of Photo-Optical Instrumentation Engineers & Society for Imaging Science and Technology. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
Liang_Hypergraph-based_Saliency_Map.pdf2.46 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

Last Week
Last month
Citations as of Jun 4, 2023


Citations as of Jun 4, 2023

Google ScholarTM



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