当前位置:网站首页>【图像融合】基于NSST结合PCNN实现图像融合附matlab代码
【图像融合】基于NSST结合PCNN实现图像融合附matlab代码
2022-06-24 06:41:00 【Matlab科研工作室】
1 简介
目的:融合PET/CT/MRI医学图像,使结果图像尽可能包含更多边缘和纹理特征等信息,以更好地区分病变,肿瘤与正常组织器官,为疾病诊断提供更多的有用信息.方法:提出一种基于非下采样剪切波变换(NSST)和脉冲耦合神经网络(PCNN)模型的融合方法.首先,根据图像局部区域能量和,对图像NSST低频系数进行加权融合;然后,根据PCNN神经元的点火次数,选择图像NSST高频方向系数;最后,通过逆NSST变换,得到融合后的图像.结果:分别对7组MRI/PET和CT/PET图像进行融合实验,其结果图像具有很好的视觉效果,且在互信息,边缘相似性,梯度相似性及空间频率4个指标综合评价中较其它算法更优.结论:本方法可以自适应捕获边缘和纹理信息,具有良好的融合效果.
2 部分代码
clear all;close all;clc;%% NSST tool boxaddpath(genpath('shearlet'));%%A=imread('sourceimages/s02_MR.tif'); %anatomical imageB=imread('sourceimages/s02_PET.tif'); %functional imageimg1 = double(A)/255;img2 = double(B)/255;img2_YUV=ConvertRGBtoYUV(img2);img2_Y=img2_YUV(:,:,1);[hei, wid] = size(img1);% image fusion with NSST-PAPCNNimgf_Y=fuse_NSST_PAPCNN(img1,img2_Y);imgf_YUV=zeros(hei,wid,3);imgf_YUV(:,:,1)=imgf_Y;imgf_YUV(:,:,2)=img2_YUV(:,:,2);imgf_YUV(:,:,3)=img2_YUV(:,:,3);imgf=ConvertYUVtoRGB(imgf_YUV);F=uint8(imgf*255);figure;subplot(131);imshow(A);title('图1')subplot(132);imshow(B);title('图2')subplot(133);imshow(F);title('融合图');imwrite(F,'results/fused.tif');
3 仿真结果

4 参考文献
[1]田娟秀, 刘国才. 基于NSST变换和PCNN的医学图像融合方法[J]. 中国医学物理学杂志, 2018, 35(8):7.
博主简介:擅长智能优化算法、神经网络预测、信号处理、元胞自动机、图像处理、路径规划、无人机等多种领域的Matlab仿真,相关matlab代码问题可私信交流。
部分理论引用网络文献,若有侵权联系博主删除。
边栏推荐
- Unexpected token u in JSON at position 0
- 成为 TD Hero,做用技术改变世界的超级英雄 | 来自 TDengine 社区的邀请函
- OMX的初始化流程
- Open source and innovation
- With a goal of 50million days' living, pwnk wants to build a "Disneyland" for the next generation of young people
- 雲監控系統 HertzBeat v1.1.0 發布,一條命令開啟監控之旅!
- 0 foundation a literature club low code development member management applet (6)
- An example of MySQL accidental deletion recovery - using Myflash
- 【pointNet】基于pointNet的三维点云目标分类识别matlab仿真
- Arduino raised $32million to enter the enterprise market
猜你喜欢

取模软件 模拟显示验证取模数据正确性 逆向 把点阵数组bin文件转显示

开源与创新

JVM调试工具-Arthas
![[Yugong series] June 2022 asp Basic introduction and use of cellreport reporting tool under net core](/img/18/1576cb7bdae5740828d1db5b283aee.png)
[Yugong series] June 2022 asp Basic introduction and use of cellreport reporting tool under net core

华为云数据库进阶学习

RealNetworks vs. 微软:早期流媒体行业之争

Huawei cloud database advanced learning
![[cloud based co creation] overview of the IOT of Huawei cloud HCIA IOT v2.5 training series](/img/80/1be6a87639ac8da41bc881b3341646.png)
[cloud based co creation] overview of the IOT of Huawei cloud HCIA IOT v2.5 training series

Decryption of the original divine square stone mechanism

Become TD hero, a superhero who changes the world with Technology | invitation from tdengine community
随机推荐
为什么要用lock 【readonly】object?为什么不要lock(this)?
Web messaging and woker classification: talking about the cross thread and cross page communication of PostMessage
setInterval里面的函数不能有括号
Use of SQL join
成为 TD Hero,做用技术改变世界的超级英雄 | 来自 TDengine 社区的邀请函
The data synchronization tool dataX has officially supported reading and writing tdengine
JVM debugging tool -jvisualvm
如何删除/选择电脑上的输入法
Application configuration management, basic principle analysis
The cloud monitoring system hertzbeat V1.1.0 is released, and a command starts the monitoring journey!
Clickhouse source code note 6: exploring the sorting of columnar storage systems
Coding helps promote the internationalization of Tencent games
Spark项目打包优化实践
OMX的初始化流程
LuChen technology was invited to join NVIDIA startup acceleration program
JVM调试工具-jvisualvm
Le système de surveillance du nuage hertzbeat v1.1.0 a été publié, une commande pour démarrer le voyage de surveillance!
How do I check the IP address? What is an IP address
【问题解决】虚拟机配置静态ip
Can the small fire Chunfeng tea make its debut by "keeping fit"?