【手写数字识别】基于matlab BP神经网络手写数字识别【含Matlab源码 3133期】.zip

% 数字识别 % 生成输入向量和目标向量 clear all; 'LOADING......' for kk = 0:99 p1=ones(16,16); %建立全为1的样本矩阵 m=strcat('nums\',int2str(kk),'.bmp'); x=imread(m,'bmp'); %循环读入0-99个样本数字文件 bw=im2bw(x,0.5); %对输入图像进行二值化处理 采用全局阈值0.5 [i,j]=find(bw==0); imin=min(i); imax=max(i); jmin=min(j); jmax=max(j); bw1=bw(imin:imax,jmin:jmax); %截取是入图像中的数字部分 rate=16/max(size(bw1)); bw1=imresize(bw1,rate); %对输入文件变尺寸处理 [i,j]=size(bw1); i1=round((16-i)/2); j1=round((16-j)/2); p1(i1+1:i1+i,j1+1:j1+j)=bw1; %建立起16*16的矩阵 p1=-1.*p1+ones(16,16); %反色处理 for m=0:15 p(m*16+1:(m+1)*16,kk+1)=p1(1:16,m+1); end %将处理的源样本输入供神经网络训练的样本 pcolum是样本数循环变量 switch kk case{0,10,20,30,40,50,60,70,80,90} t(kk+1)=0; %数字0 case{1,11,21,31,41,51,61,71,81,91} t(kk+1)=1; %数字1 case{2,12,22,32,42,52,62,72,82,92} t(kk+1)=2; %数字2 case{3,13,23,33,43,53,63,73,83,93} t(kk+1)=3; %数字3 case{4,14,24,34,44,54,64,74,84,94} t(kk+1)=4; %数字4 case{5,15,25,35,45,55,65,75,85,95} t(kk+1)=5; %数字5 case{6,16,26,36,46,56,66,76,86,96} t(kk+1)=6; %数字6 case{7,17,27,37,47,57,67,77,87,97} t(kk+1)=7; %数字7 case{8,18,28,38,48,58,68,78,88,98} t(kk+1)=8; %数字8 case{9,19,29,39,49,59,69,79,89,99} t(kk+1)=9; %数字9 end end %建立与训练样本对应的输出值t 'LOAD OK.' save E52PT p t; % 创建和训练BP网络 clear all; load E52PT p t; %加载样本 pr(1:256,1)=0; pr(1:256,2)=1; %创建BP网络 net=newff(pr,[25 1],{'logsig' 'purelin'}, 'traingdx', 'learngdm'); net.trainParam.epochs=2500; %设置训练步数 net.trainParam.goal=0.001; %设置训练目标 net.trainParam.show=10; %设置训练显示格数 net.trainParam.lr=0.05; %设置训练学习率 net=train(net,p,t); %训练BP网络 'TRAIN OK.' save E52net net; % 识别 for times=0:999 clear all; p(1:256,1)=1; p1=ones(16,16); load E52net net; test=input('FileName:', 's'); x=imread(test,'bmp'); bw=im2bw(x,0.5); [i,j]=find(bw==0); imin=min(i); imax=max(i); jmin=min(j); jmax=max(j); bw1=bw(imin:imax,jmin:jmax); rate=16/max(size(bw1)); bw1=imresize(bw1,rate); [i,j]=size(bw1); i1=round((16-i)/2); j1=round((16-j)/2); p1(i1+1:i1+i,j1+1:j1+j)=bw1; p1=-1.*p1+ones(16,16); for m=0:15 p(m*16+1:(m+1)*16,1)=p1(1:16,m+1); end [a,Pf,Af]=sim(net,p); %测试网络 imshow(p1); a=round(a) %输出网络识别结果 end