An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain
Multi-modality image fusion provides more comprehensive and sophisticated information in modern medical diagnosis, remote sensing, video surveillance, etc. Traditional multi-scale transform (MST) based image fusion solutions have difficulties in the selection of decomposition level, and the contrast...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-07-01
|
Series: | Entropy |
Subjects: | |
Online Access: | http://www.mdpi.com/1099-4300/20/7/522 |
_version_ | 1811308382504615936 |
---|---|
author | Yuanyuan Li Yanjing Sun Xinhua Huang Guanqiu Qi Mingyao Zheng Zhiqin Zhu |
author_facet | Yuanyuan Li Yanjing Sun Xinhua Huang Guanqiu Qi Mingyao Zheng Zhiqin Zhu |
author_sort | Yuanyuan Li |
collection | DOAJ |
description | Multi-modality image fusion provides more comprehensive and sophisticated information in modern medical diagnosis, remote sensing, video surveillance, etc. Traditional multi-scale transform (MST) based image fusion solutions have difficulties in the selection of decomposition level, and the contrast loss in fused image. At the same time, traditional sparse-representation based image fusion methods suffer the weak representation ability of fixed dictionary. In order to overcome these deficiencies of MST- and SR-based methods, this paper proposes an image fusion framework which integrates nonsubsampled contour transformation (NSCT) into sparse representation (SR). In this fusion framework, NSCT is applied to source images decomposition for obtaining corresponding low- and high-pass coefficients. It fuses low- and high-pass coefficients by using SR and Sum Modified-laplacian (SML) respectively. NSCT inversely transforms the fused coefficients to obtain the final fused image. In this framework, a principal component analysis (PCA) is implemented in dictionary training to reduce the dimension of learned dictionary and computation costs. A novel high-pass fusion rule based on SML is applied to suppress pseudo-Gibbs phenomena around singularities of fused image. Compared to three mainstream image fusion solutions, the proposed solution achieves better performance on structural similarity and detail preservation in fused images. |
first_indexed | 2024-04-13T09:20:59Z |
format | Article |
id | doaj.art-7b78fc5f746548778afda35bc6989f98 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-04-13T09:20:59Z |
publishDate | 2018-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-7b78fc5f746548778afda35bc6989f982022-12-22T02:52:35ZengMDPI AGEntropy1099-43002018-07-0120752210.3390/e20070522e20070522An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT DomainYuanyuan Li0Yanjing Sun1Xinhua Huang2Guanqiu Qi3Mingyao Zheng4Zhiqin Zhu5School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaCollege of Automation, Chongqing University, Chongqing 400044, ChinaSchool of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe 85281, AZ, USACollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaMulti-modality image fusion provides more comprehensive and sophisticated information in modern medical diagnosis, remote sensing, video surveillance, etc. Traditional multi-scale transform (MST) based image fusion solutions have difficulties in the selection of decomposition level, and the contrast loss in fused image. At the same time, traditional sparse-representation based image fusion methods suffer the weak representation ability of fixed dictionary. In order to overcome these deficiencies of MST- and SR-based methods, this paper proposes an image fusion framework which integrates nonsubsampled contour transformation (NSCT) into sparse representation (SR). In this fusion framework, NSCT is applied to source images decomposition for obtaining corresponding low- and high-pass coefficients. It fuses low- and high-pass coefficients by using SR and Sum Modified-laplacian (SML) respectively. NSCT inversely transforms the fused coefficients to obtain the final fused image. In this framework, a principal component analysis (PCA) is implemented in dictionary training to reduce the dimension of learned dictionary and computation costs. A novel high-pass fusion rule based on SML is applied to suppress pseudo-Gibbs phenomena around singularities of fused image. Compared to three mainstream image fusion solutions, the proposed solution achieves better performance on structural similarity and detail preservation in fused images.http://www.mdpi.com/1099-4300/20/7/522image fusionsparse representationNSCTSML |
spellingShingle | Yuanyuan Li Yanjing Sun Xinhua Huang Guanqiu Qi Mingyao Zheng Zhiqin Zhu An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain Entropy image fusion sparse representation NSCT SML |
title | An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain |
title_full | An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain |
title_fullStr | An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain |
title_full_unstemmed | An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain |
title_short | An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain |
title_sort | image fusion method based on sparse representation and sum modified laplacian in nsct domain |
topic | image fusion sparse representation NSCT SML |
url | http://www.mdpi.com/1099-4300/20/7/522 |
work_keys_str_mv | AT yuanyuanli animagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT yanjingsun animagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT xinhuahuang animagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT guanqiuqi animagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT mingyaozheng animagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT zhiqinzhu animagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT yuanyuanli imagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT yanjingsun imagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT xinhuahuang imagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT guanqiuqi imagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT mingyaozheng imagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain AT zhiqinzhu imagefusionmethodbasedonsparserepresentationandsummodifiedlaplacianinnsctdomain |