A novel fusion framework of visible light and infrared images based on singular value decomposition and adaptive DUAL-PCNN in NSST domain

doi:10.1016/j.infrared.2018.04.004

CIOMP OpenIR

	A novel fusion framework of visible light and infrared images based on singular value decomposition and adaptive DUAL-PCNN in NSST domain
	Cheng, B. Y.; Jin, L. X.; Li, G. N.
	2018
发表期刊	Infrared Physics & Technology
ISSN	1350-4495
卷号	91 页码:153-163
摘要	Visible light and infrared images fusion has been a significant subject in imaging science As a new contribution to this field, a novel fusion framework of visible light and infrared images based on adaptive dual-channel unit-linking pulse coupled neural networks with singular value decomposition (ADSPCNN) in non-subsampled shearlet transform (NSST) domain is present in this paper. First, the source images are decomposed into multi-direction and multi-scale sub-images by NSST. Furthermore, an improved novel sum modified-Laplacian (INSML) of low-pass sub-image and an improved average gradient (IAVG) of high-pass sub-images are input to stimulate the ADS-PCNN, respectively. To address the large spectral difference between infrared and visible light and the occurrence of black artifacts in fused images, a local structure information operator (LSI), which comes from local area singular value decomposition in each source image, is regarded as the adaptive linking strength that enhances fusion accuracy. Compared with PCNN models in other studies, the proposed method simplifies certain peripheral parameters, and the time matrix is utilized to decide the iteration number adaptively A series of images from diverse scenes are used for fusion experiments and the fusion results are evaluated subjectively and objectively. The results of the subjective and objective evaluation show that our algorithm exhibits superior fusion performance and is more effective than the existing typical fusion techniques. (C) 2018 Elsevier B. V. All rights reserved.
关键词	NSST ADS-PCNN Image fusion Singular value decomposition Local structure information operator Linking strength shearlet transform feature-extraction nsct domain algorithm scheme Instruments & Instrumentation Optics Physics
DOI	10.1016/j.infrared.2018.04.004
收录类别	SCI ; EI
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/60874
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	Cheng, B. Y.,Jin, L. X.,Li, G. N.. A novel fusion framework of visible light and infrared images based on singular value decomposition and adaptive DUAL-PCNN in NSST domain[J]. Infrared Physics & Technology,2018,91:153-163.
APA	Cheng, B. Y.,Jin, L. X.,&Li, G. N..(2018).A novel fusion framework of visible light and infrared images based on singular value decomposition and adaptive DUAL-PCNN in NSST domain.Infrared Physics & Technology,91,153-163.
MLA	Cheng, B. Y.,et al."A novel fusion framework of visible light and infrared images based on singular value decomposition and adaptive DUAL-PCNN in NSST domain".Infrared Physics & Technology 91(2018):153-163.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
A novel fusion frame（3524KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文