【MATLAB图像融合】[14]PCNN脉冲耦合神经网络代码分享

本代码转自厦门大学屈小波教授的DEMO代码。

% Demo for PCNN in image processing% ---------% Author: Qu Xiao-Bo <qxb_xmu [at] > Aug.28,%Postal address:% Rom 509, Scientific Research Building # 2,Haiyun Campus, Xiamen University,Xiamen,Fujian, P. R. China, 361005% Website:https://csrc./ %=============================================================% References:% [1]Qu Xiao-Bo, YAN Jing-Wen, XIAO Hong-Zhi, ZHU Zi-Qian. Image Fusion Algorithm Based on Spatial Frequency-Motivated Pulse Coupled Neural Networks in Nonsubsampled Contourlet Transform Domain. Acta Automatica Sinica, Vol.34, No.12, pp: 1508-1514.Dec.. % [2]Xiao-Bo Qu,Jingwen Yan.Image Fusion Algorithm Based on Features Motivated Multi-channel Pulse Coupled Neural Networks, The 2nd International Conference on Bioinformatics and Biomedical Engineering-iCBBE，Shanghai, China, 16-18 May , pp. 2103-2106% [3]Xiaobo Qu, Changwei Hu, Jingwen Yan, Image Fusion Algorithm Based On Orientation Information Motivated Pulse Coupled Neural Networks, The seventh World Congress on Intelligent Control and Automation-WCICA ，Chongqing, China,25-27 June , pp.2437-2441% [4]Xiaobo Qu, Jingwen Yan, Ziqian Zhu, et al. Multi-focus image fusion algorithm based on regional firing characteristic of Pulse Coupled Neural Networks, Conference Pre-proceedings of The Second International Conference on Bio-Inspired Computing: Theories and Applications, pp:563-565,% [5]Yan Jingwen, QU Xiaobo. Beyond Wavelets and Its Applications [M].Beijing: National Defense Industry Press, June .(In Chinese)%=============================================================%%clc;clear all;close all;%%im=imread('2.jpg');im=double(im);%%link_arrange=6;iteration_times=200;%%firing_times=PCNN_large_arrange(im,link_arrange,iteration_times);%%figure,imshow(im,[])figure,imshow(firing_times,[])

function [normalized_matrix,cmin,cmax]=Normalized(matrix)% function [normalized_matrix,cmin,cmax]=Normalized(matrix)% Computes the normalized form of matrix% Input: matrix, denotes an image% Output: normalized_matrix,normalized form of matrix% cmin, is the is the smallest element in matrix% cman is the is the largest element in matrix% ---------% Author: Qu Xiao-Bo <qxb_xmu [at] > Aug.28,%Postal address:% Rom 509, Scientific Research Building # 2,Haiyun Campus, Xiamen University,Xiamen,Fujian, P. R. China, 361005% Website: http://quxiaobo.%=============================================================% References:% [1]Qu Xiao-Bo, YAN Jing-Wen, XIAO Hong-Zhi, ZHU Zi-Qian. Image Fusion Algorithm Based on Spatial Frequency-Motivated Pulse Coupled Neural Networks in Nonsubsampled Contourlet Transform Domain. Acta Automatica Sinica, Vol.34, No.12, pp: 1508-1514.Dec.. % [2]Xiao-Bo Qu,Jingwen Yan.Image Fusion Algorithm Based on Features Motivated Multi-channel Pulse Coupled Neural Networks, The 2nd International Conference on Bioinformatics and Biomedical Engineering-iCBBE，Shanghai, China, 16-18 May , pp. 2103-2106% [3]Xiaobo Qu, Changwei Hu, Jingwen Yan, Image Fusion Algorithm Based On Orientation Information Motivated Pulse Coupled Neural Networks, The seventh World Congress on Intelligent Control and Automation-WCICA ，Chongqing, China,25-27 June , pp.2437-2441% [4]Xiaobo Qu, Jingwen Yan, Ziqian Zhu, et al. Multi-focus image fusion algorithm based on regional firing characteristic of Pulse Coupled Neural Networks, Conference Pre-proceedings of The Second International Conference on Bio-Inspired Computing: Theories and Applications, pp:563-565,% [5]Yan Jingwen, QU Xiaobo. Beyond Wavelets and Its Applications [M].Beijing: National Defense Industry Press, June .(In Chinese)%=============================================================% Get absolute value of matrixinput_matrix=abs(matrix);Max_input=max(input_matrix(:));Min_input=min(input_matrix(:));min_matrix=ones(size(input_matrix)).*Min_input;normalized_matrix=(input_matrix-min_matrix)./(Max_input-Min_input+eps);cmin=Min_input;cmax=Max_input;%

function R=PCNN_large_arrange(matrix,link_arrange,np,pre_flag)% R=PCNN_large_arrange(matrix,link_arrange,np,pre_flag)% compute the fire times of each pixel in the PCNN % np is the iterative times% R is the fire times of coefficients of wavelet decomposition% ---------% Author: Qu Xiao-Bo <qxb_xmu [at] > Aug.28,%Postal address:% Rom 509, Scientific Research Building # 2,Haiyun Campus, Xiamen University,Xiamen,Fujian, P. R. China, 361005% Website: https://csrc./ %=============================================================% References:% [1]Qu Xiao-Bo, YAN Jing-Wen, XIAO Hong-Zhi, ZHU Zi-Qian. Image Fusion Algorithm Based on Spatial Frequency-Motivated Pulse Coupled Neural Networks in Nonsubsampled Contourlet Transform Domain. Acta Automatica Sinica, Vol.34, No.12, pp: 1508-1514.Dec.. % [2]Xiao-Bo Qu,Jingwen Yan.Image Fusion Algorithm Based on Features Motivated Multi-channel Pulse Coupled Neural Networks, The 2nd International Conference on Bioinformatics and Biomedical Engineering-iCBBE，Shanghai, China, 16-18 May , pp. 2103-2106% [3]Xiaobo Qu, Changwei Hu, Jingwen Yan, Image Fusion Algorithm Based On Orientation Information Motivated Pulse Coupled Neural Networks, The seventh World Congress on Intelligent Control and Automation-WCICA ，Chongqing, China,25-27 June , pp.2437-2441% [4]Xiaobo Qu, Jingwen Yan, Ziqian Zhu, et al. Multi-focus image fusion algorithm based on regional firing characteristic of Pulse Coupled Neural Networks, Conference Pre-proceedings of The Second International Conference on Bio-Inspired Computing: Theories and Applications, pp:563-565,% [5]Yan Jingwen, QU Xiaobo. Beyond Wavelets and Its Applications [M].Beijing: National Defense Industry Press, June .(In Chinese)%=============================================================disp('PCNN is processing...')[p,q]=size(matrix);% computes the normalized matrix of the matrixA and matrixBF_NA=Normalized(matrix);%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Initialize the parameters. % You'd better change them according to your applications alpha_L=1;alpha_Theta=0.2;beta=3;vL=1.00;vTheta=20;% Generate the null matrix that could be usedL=zeros(p,q);U=zeros(p,q);Y=zeros(p,q);Y0=zeros(p,q);Theta=zeros(p,q);% Compute the linking strength.center_x=round(link_arrange/2);center_y=round(link_arrange/2);W=zeros(link_arrange,link_arrange);for i=1:link_arrangefor j=1:link_arrangeif (i==center_x)&&(j==center_y)W(i,j)=0;elseW(i,j)=1./sqrt((i-center_x).^2+(j-center_y).^2);endendend%%%%%%%%%%%%%%%%%%%%%%%%%%%F=F_NA;for n=1:npK=conv2(Y,W,'same');L=exp(-alpha_L)*L+vL*K;Theta=exp(-alpha_Theta)*Theta+vTheta*Y;U=F.*(1+beta*L);Y=im2double(U>Theta);Y0=Y0+Y; endR=Y0;

运行结果：

链接强度为6，迭代次数为200次。

代码可稳健运行。

如果觉得《【MATLAB图像融合】[14]PCNN脉冲耦合神经网络代码分享》对你有帮助，请点赞、收藏，并留下你的观点哦！