|本期目录/Table of Contents|

[1]潘树伟,戴文战,李俊峰.基于纹理特征与广义相关性结构信息的医学图像融合[J].浙江理工大学学报,2017,37-38(自科3):423-431.
 PAN Shuwei,DAI Wenzhan,LI Junfeng.Medical Image Fusion Algorithm Based on Textural Features and Generalized Correlation Structure Information[J].Journal of Zhejiang Sci-Tech University,2017,37-38(自科3):423-431.
点击复制

基于纹理特征与广义相关性结构信息的医学图像融合()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第37-38卷
期数:
2017年自科3期
页码:
423-431
栏目:
出版日期:
2017-05-18

文章信息/Info

Title:
Medical Image Fusion Algorithm Based on Textural Features and Generalized Correlation Structure Information
文章编号:
1673-3851 (2017) 03-0423-09
作者:
潘树伟戴文战李俊峰
1.浙江理工大学自动化研究所,杭州 310012;2. 浙江工商大学信息与电子工程学院,杭州 310012
Author(s):
PAN Shuwei DAI Wenzhan LI Junfeng
1. Institute of Automation, Zhejiang Sci-Tech University, Hangzhou 310018,China; 2. School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou 310018, China
关键词:
医学图像融合非下采样Contourlet变换局部差分计盒维数广义相关性结构信息
分类号:
TP391.4
文献标志码:
A
摘要:
结合多尺度变换的图像特征,提出了一种基于纹理特征与相关性结构信息的医学图像融合方法。首先对已配准的源图像进行非下采样Contourlet变换,得到低频、高频子带系数。其次考虑人眼视觉对纹理特征的敏感性,提出局部差分计盒维数来统计图像的纹理信息;分析NSCT高频子带兄弟系数间及其父子系数间的强相关性,分别计算出系数间的结构相似度与邻域拉普拉斯能量和,作为高频子带系数间的广义相关性结构信息。然后对低频提出Sigmoid函数自适应融合,对高频采用广义相关性结构信息取大法。最后进行逆NSCT变换得到融合图像。通过灰度与彩色图像融合实验发现,该算法不仅可以保留源图像的边缘信息,还得到较好的客观评价指标和视觉效果。

参考文献/References:

[1] DAS S, KUNDU M K. A neurofuzzy approach for medical image fusion[J]. IEEE Transactions on Biomedical Engineering,2013,60(12):3347-3353.
[2] BHATNAGAR G, WU Q M J, LIU Z. Directive contrast based multimodal medical image fusion in NSCT domain[J]. IEEE Transactions on Multimedia,2013,15(5):1014-1024.
[3] WANG L, LI B, TIAN L. Multimodal medical volumetric data fusion using 3D discrete shearlet transform and globaltolocal rule[J]. IEEE Transactions on Biomedical Engineering,2014,61(1):197-206.
[4] DAS S, KUNDU M K. NSCTbased multimodal medical image fusion using pulsecoupled neural network and modified spatial frequency[J]. Medical & Biological Engineering & Computing,2012,50(10):1105-1114.
[5] HEIJMANS H M, GOUTSIAS J. Nonlinear multiresolution signal decomposition schemes. II. Morphological wavelets [J]. Image Processing, IEEE Transactions on,2000,9(11):1897-1913.
[6]李俊峰,姜晓丽,戴文战.基于提升小波变换的医学图像融合[J].中国图象图形学报,2014,19(11):1639-1648.
[7] YANG Y, QUE Y, HUANG S, et al. Multimodal sensor medical image fusion based on type2 fuzzy logic in NSCT domain[J]. IEEE Sensors Journal,2016,16(10):3735-3745.
[8] SRIVASTAVA R, PRAKASH O, KHARE A. Local energybased multimodal medical image fusion in curvelet domain[J]. IET Computer Vision,2016,10(6):513-527.
[9] BHATEJA V, PATEL H, KRISHN A, et al. Multimodal medical image sensor fusion framework using cascade of wavelet and contourlet transform domains[J]. IEEE Sensors Journal,2015,15(12):6783-6790.
[10] CUNHA A L, ZHOU J P, DO M N. The nonsubsampled contourlet transform:theory, design and applications[J]. IEEE Transactions on Image Processing.2006,15(10):3089-3101.

相似文献/References:

[1]李加恒,戴文战,李俊峰.基于互信息的多模态医学图像融合[J].浙江理工大学学报,2016,35-36(自科4):607.
 LI Jiaheng,DAI Wenzhan,LI Junfeng.Multimodality Medical Image Fusion Based on Mutual Information[J].Journal of Zhejiang Sci-Tech University,2016,35-36(自科3):607.
[2]殷鑫华,戴文战,李俊峰.基于在线字典学习的自适应医学图像融合算法[J].浙江理工大学学报,2017,37-38(自科2):246.
 YIN Xinhua,DAI Wenzhan,LI Junfen.Adaptive Medical Image Fusion Algorithm Based onOnline Dictionary Learning[J].Journal of Zhejiang Sci-Tech University,2017,37-38(自科3):246.

备注/Memo

备注/Memo:
收稿日期: 2016-10-16
网络出版日期:2017-01-03
基金项目: 国家自然科学基金项目(61374022)
作者简介: 潘树伟(1990-),男,浙江湖州人,硕士研究生,主要从事模式识别与图像处理方面的研究
通信作者: 戴文战,E-mail: dwz@zisu.edu.cn
更新日期/Last Update: 2017-09-13