【图像压缩】基于PCNN实现图像的压缩重建附matlab代码

最新推荐文章于 2023-09-14 15:12:37 发布

原创最新推荐文章于 2023-09-14 15:12:37 发布 · 144 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#matlab #图像处理 #算法

图像处理专栏收录该内容

871 篇文章

订阅专栏

这篇博客详细介绍了1-D脉冲耦合神经网络(Pulse-Coupled Neural Network, PCNN)的实现过程，通过Matlab代码展示了如何计算各个状态变量的变化，并提供了初始化参数和仿真结果。作者分享了PCNN在图像分割压缩编码中的应用实例，适合对神经网络和信号处理感兴趣的读者。

1 简介

2 部分代码

%   The PCNN 1-D demo code was written by Kun Zhan%   $Revision: 1.0.0.0 $  $Date: 2016/03/25 $ 20:25:48 $%   Reference:%   K Zhan, J Shi, H Wang, Y Xie, Q Li, %   "Computational Mechanisms of %   Pulse-Coupled Neural Networks: A Comprehensive Review,"%   Archives of Computational Methods in Engineering, 2016.clearT = 40;s = [0.5 0.35 0.5 0.8 0.63 0.5 0.99];[~, n] = size(s);Y = zeros(T+1,n); F = Y; L = F; E = F + 1; U = F;for t = 1:T;    K = conv(Y(t,:),[0.707 1 0.707],'same');    F(t+1,:) = exp(-0.2).*F(t,:) +  0.1*K + s;    L(t+1,:) = exp(-0.5).*L(t,:) + 0.2.*K;    U(t+1,:) = F(t+1,:).*(1+0.5*L(t+1,:));    E(t+1,:) = exp(-0.2).*E(t,:) + 6.*Y(t,:);    Y(t+1,:) = double(U(t+1,:)>E(t+1,:));endt = [0:1:T];c = (n+1)./2;figure(1)plot(t,E(:,c),'k-d',...     t,U(:,c),'b-s',...     t,F(:,c),'g*-',...     t,L(:,c),'m+-')axis square, axis([0 40 0 15])h = legend('$\Theta_{ij}(n)$','$U_{ij}(n)$',...    '$F_{ij}(n)$','$L_{ij}(n)$',1);set(h,'Interpreter','latex')title('$f=0.8,g=0.8,\Theta_{ij}(0)=1, U_{ij}(0)=0,\forall i,j$','Interpreter','latex')xlabel('Iterative time \it{n}')figure(2),stem(t,Y(:,c))axis([0 40 0 1.2])