Medical image fusion method based on guided filter

Pan GUO; Wen-chao HE; Long-kai LIANG; Meng ZHANG; Xu-hao LYU; Xin GONG

doi:10.3788/YJYXS20193406.0605

您当前的位置：

首页 >

文章列表页 >

Medical image fusion method based on guided filter

Image Processing | 更新时间：2020-07-05

- Medical image fusion method based on guided filter
- Chinese Journal of Liquid Crystals and Displays Vol. 34, Issue 6, Pages: 605-612(2019)
- 作者机构：
  
  1.东北师范大学人文学院理工学院, 吉林长春 130117
  2.吉林省高校汽车电子技术工程研究中心, 吉林长春 130011
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20193406.0605
  CLC： TP391.41
- Received：05 December 2018，
  
  Accepted：23 March 2019，
  
  Published：05 June 2019
- 稿件说明：
移动端阅览
Pan GUO, Wen-chao HE, Long-kai LIANG, et al. Medical image fusion method based on guided filter[J]. Chinese journal of liquid crystals and displays, 2019, 34(6): 605-612.
DOI：

Pan GUO, Wen-chao HE, Long-kai LIANG, et al. Medical image fusion method based on guided filter[J]. Chinese journal of liquid crystals and displays, 2019, 34(6): 605-612. DOI： 10.3788/YJYXS20193406.0605.

摘要

针对医学图像融合过程中易产生人造纹理的问题，本文将引导滤波器应用到医学图像融合中，有效提高融合图像的空间连续性，减少人造纹理的产生。首先利用导向滤波器的细节增强特性获得图像的细节层信息，主要通过导向滤波器对原图像进行滤波处理得到其基础层图像信息，再与原图像作差运算即可得细节层图像信息；然后采用基于含可变参数

的邻域统计特性融合规则得到图像融合权值系数，该融合规则在原有的邻域统计特性中加入可变参数

，可以有效增强融合图像的细节信息；最后将原图像按照所得的图像融合权值系数进行融合，得到最终的融合图像。实验仿真结果对比分析表明，随着可变参数

的变化，融合效果也有明显的提高，当

10后，融合效果基本趋于平稳。该融合方法可以有效地实现医学图像融合，与其他融合方法相比，具有一定的优越性。

Abstract

Aiming at the problem that artificial texture is easy to be produced in the process of medical image fusion

the guiding filter was applied to medical image fusion to effectively improve the spatial continuity of fusion image and reduce the generation of artificial texture. Firstly

the detail layer information of the image was obtained by using the detail enhancement characteristic of the guide filter. The basic layer image information was obtained by filtering the original image through the guide filter

and then the detail layer image information could be obtained by the difference operation between the original image and the guide filter. Then

the image fusion weight coefficient was obtained based on the neighborhood statistical characteristics fusion rule with variable parameter

. The fusion rule added variable parameter

to the original neighborhood statistical characteristics

which could effectively enhance the details of the fusion image. Finally

the original image was fused according to the obtained image fusion weight coefficient to obtain the final fusion image. The comparison and analysis of experimental simulation results indicate that the fusion effect is significantly improved with the change of variable parameter

. The fusion effect is basically stable after

10. This fusion algorithm can effectively realize medical image fusion and has certain advantages over other fusion methods.

关键词

Keywords

references

刘帅奇, 郑伟, 赵杰, 等.数字图像融合算法分析与应用[M].北京:机械工业出版社, 2018:4.

LIU S Q, ZHENG W, ZHAO J, et al . Analysis and Application of Algorithm for Digital Image Fusion [M]. Beijing:China Machine Press, 2018:4. (in Chinese)

杨波.基于小波的像素级图像融合算法研究[D].上海: 上海交通大学, 2008.

YANG B. Research on wavelet-based pixel-level image fusion algorithms[D]. Shanghai: Shanghai Jiao Tong University, 2008. (in Chinese)

LEE DD, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature , 1999, 401(6755):788-791.

LEE DD, SEBASTIAN S H. Algorithms for non-negative matrix factorization[J]. Advances in Neural Information Processing Systems , 2001, 13:556-562.

SINGH R, VATSA M, NOORE A. Multimodal medical image fusion using redundant discrete wavelet transform[C]// Proceedings of 2009 Seventh International Conference on Advances in Pattern Recognition . Kolkata, India: IEEE, 2009.

DACUNHA A L, ZHOU J, DO M N. The nonsubsampled contourlet transform:Theory, design, and applications[J]. IEEE Transactions on Image Processing , 2006, 15(10):3089-3101.

XING X X, LIU F, SHANG W W, et al . Medical image fusion in compressed sensing based on non-subsampled contourlet transform[C]// Proceedings of 2013 IEEE 9th International Conference on Mobile Ad-hoc and Sensor Networks . Dalian, China: IEEE, 2013.

王雷, 李彬, 田联房.基于平移不变剪切波变换的医学图像融合[J].华南理工大学学报:自然科学版, 2011, 39(12):13-19.

WANG L, LI B, TIAN L F. Medical image fusion based on shift-invariant shearlet transformation[J]. Journal of South China University of Technology : Natural Science Edition , 2011, 39(12):13-19. (in Chinese)

方静, 罗高鹏.改进快速NSST的热烟羽红外与可见光图像融合[J].激光与红外, 2017, 47(7):914-920.

FANG J, LUO G P. Infrared and visible images fusion of thermal plume based on rapid non-subsampled shearlet transform[J]. Laser & Infrared , 2017, 47(7):914-920. (in Chinese)

葛雯, 姬鹏冲, 赵天臣. NSST域改进NMF的红外与可见光图像融合[J].光电工程, 2016, 43(4):73-77, 83.

GE W, JI P C, ZHAO T C. Infrared and visible light images fusion of improved NMF on NSST domain[J]. Opto - Electronic Engineering , 2016, 43(4):73-77, 83. (in Chinese)

邢笑雪.基于NSST的图像融合算法研究[D].长春: 吉林大学, 2014.

XING X X. Research on the image fusion algorithm based on Non-Sumsampled Shearlet Transform[D]. Changchun: Jilin University, 2014. (in Chinese)

HE K M, SUN J, TANG X O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013, 35(6):1397-1409.

刘帅奇, 胡绍海, 赵杰, 等.结合向导滤波与复轮廓波变换的多聚焦图像融合算法[J].信号处理, 2016, 32(3):276-286.

LIU S Q, HU S H, ZHAO J, et al . Multi-focus image fusion using guided filtering and complex contourlet transform[J]. Journal of Signal Processing , 2016, 32(3):276-286. (in Chinese)

LIU S Q, SHI M Z, ZHU Z H, et al . Image fusion based on complex-shearlet domain with guided filtering[J]. Multidimensional Systems and Signal Processing , 2017, 28(1):207-224.

SHAH P, MERCHANT S M, DESAI U B. An efficient adaptive fusion scheme for multifocus images in wavelet domain using statistical properties of neighborhood[C]// Proceedings of the 14th International Conference on Information Fusion . Chicago, USA: IEEE, 2011.

KUMAR B K S. Image fusion based on pixel significance using cross bilateral filter[J]. Signal , Image and Video Processing , 2015, 9(5):1193-1204.

BAVIRISETTI D P, KOLLU V, GANG X, et al . Fusion of MRI and CT images using guided image filter and image statistics[J]. International Journal of Imaging Systems and Technology , 2017, 27(3):227-237.

刘莹.图像纹理的特征提取和分类方法研究[D].武汉: 华中科技大学, 2013.

LIU Y. Research on the method of image texture feature extraction and classification[D]. Wuhan: Huazhong University of Science and Technology, 2013. (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Robust stitching method for borehole wall images under multi-interference imaging conditions

Image defogging algorithm based on multi-scale residual feature fusion

Infrared and visible image fusion algorithm based on structure-texture decomposition

Laboratory flame image segmentation and recognition by fusing infrared and visible light

Fusion of NSCT infrared and visible images based on improved FT saliency detection

Related Author

LUO Qi

XU Wangming

LI Yaoxiang

ZHAO Yuhang

XIE Xindan

LI Xiaoyan

WANG Peng

DI Ruohai

Related Institution

School of Information Science and Engineering， Wuhan University of Science and Technology

School of Electronics and Information Engineering， Xi'an Technological University

School of Optoelectronic Engineering， Xi'an Technological University

School of Mechanical and Electrical Engineering， Xi'an Technological University

College of Electronic Information and Artificial Intelligence， Shaanxi University of Science and Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰