#-*- coding:UTF-8 -*-import urllib,urllib2,cookielib,string,Imagedef getchk(number): #創(chuàng)建cookie對象 cookie = cookielib.LWPCookieJar() cookieSupport= urllib2.HTTPCookieProcessor(cookie) opener = urllib2.build_opener(cookieSupport, urllib2.HTTPHandler) urllib2.install_opener(opener) #首次與教務(wù)系統(tǒng)鏈接獲得cookie# #偽裝browser headers = { 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', 'Accept-Encoding':'gzip,deflate', 'Accept-Language':'zh-CN,zh;q=0.8', 'User-Agent':'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.111 Safari/537.36' } req0 = urllib2.Request(  url ='http://mis.teach.ustc.edu.cn',  headers = headers  #請求頭 ) # 捕捉http錯誤 try : result0 = urllib2.urlopen(req0) except urllib2.HTTPError,e: print e.code #提取cookie getcookie = ['',] for item in cookie: getcookie.append(item.name) getcookie.append("=") getcookie.append(item.value) getcookie = "".join(getcookie)  #修改headers headers["Origin"] = "http://mis.teach.ustc.edu.cn" headers["Referer"] = "http://mis.teach.ustc.edu.cn/userinit.do" headers["Content-Type"] = "application/x-www-form-urlencoded" headers["Cookie"] = getcookie for i in range(number): req = urllib2.Request(  url ="http://mis.teach.ustc.edu.cn/randomImage.do?date='1469451446894'",  headers = headers   #請求頭 ) response = urllib2.urlopen(req) status = response.getcode() picData = response.read() if status == 200:  localPic = open("./source/"+str(i)+".jpg", "wb")  localPic.write(picData)  localPic.close() else:  print "failed to get Check Code "if __name__ == '__main__': getchk(500)

mydir='./source/';bw = './bw/';if mydir(end)~='/' mydir=[mydir,'/'];endDIRS=dir([mydir,'*.jpg']); %擴展名n=length(DIRS);for i=1:n if ~DIRS(i).isdir img = imread(strcat(mydir,DIRS(i).name )); img = rgb2gray(img);%灰度化 img = im2bw(img);%0-1二值化 name = strcat(bw,DIRS(i).name) imwrite(img,name); endend

mydir='./bw/';letter = './letter/';if mydir(end)~='/' mydir=[mydir,'/'];endDIRS=dir([mydir,'*.jpg']); %擴展名n=length(DIRS);for i=1:n if ~DIRS(i).isdir img = imread(strcat(mydir,DIRS(i).name )); img = im2bw(img);%二值化 img = 1-img;%顏色反轉(zhuǎn)讓字符成為聯(lián)通域，方便去除噪點 for ii = 0:3  region = [ii*20+1,1,19,20];%把一張驗證碼分成四個20*20大小的字符圖片  subimg = imcrop(img,region);  imlabel = bwlabel(subimg);%  imshow(imlabel);   if max(max(imlabel))>1 % 說明有噪點，要去除%   max(max(imlabel)) %   imshow(subimg);   stats = regionprops(imlabel,'Area');  area = cat(1,stats.Area);  maxindex = find(area == max(area));  area(maxindex) = 0;    secondindex = find(area == max(area));   imindex = ismember(imlabel,secondindex);  subimg(imindex==1)=0;%去掉第二大連通域，噪點不可能比字符大，所以第二大的就是噪點  end  name = strcat(letter,DIRS(i).name(1:length(DIRS(i).name)-4),'_',num2str(ii),'.jpg')  imwrite(subimg,name); end endend

if mydir(end)~='/' mydir=[mydir,'/'];endDIRS=dir([mydir,'*.jpg']); %擴展名n=length(DIRS);for i=1:n if ~DIRS(i).isdir img = imread(strcat(mydir,DIRS(i).name )); img = im2bw(img); minwidth = 20; for angle = -60:60  imgr=imrotate(img,angle,'bilinear','crop');%crop 避免圖像大小變化  imlabel = bwlabel(imgr);  stats = regionprops(imlabel,'Area');  area = cat(1,stats.Area);  maxindex = find(area == max(area));  imindex = ismember(imlabel,maxindex);%最大連通域為1  [y,x] = find(imindex==1);  width = max(x)-min(x)+1;  if width<minwidth  minwidth = width;  imgrr = imgr;  end end name = strcat(rotate,DIRS(i).name) imwrite(imgrr,name); endend

mydir='./test/';samples = './samples/';if mydir(end)~='/' mydir=[mydir,'/'];endif samples(end)~='/' samples=[samples,'/'];endDIRS=dir([mydir,'*.jpg']); %擴展?DIRS1=dir([samples,'*.jpg']); %擴展名n=length(DIRS);%驗證碼總圖數(shù)singleerror = 0;%單個錯誤uniterror = 0;%一張驗證碼錯誤個數(shù)for i=1:n if ~DIRS(i).isdir realcodes = DIRS(i).name(1:4); fprintf('驗證碼實際字符:%s/n',realcodes); img = imread(strcat(mydir,DIRS(i).name )); img = rgb2gray(img); img = im2bw(img); img = 1-img;%顏色反轉(zhuǎn)讓字符成為聯(lián)通域 subimgs = []; for ii = 0:3  region = [ii*20+1,1,19,20];%奇怪,為什么這樣才能均分？  subimg = imcrop(img,region);  imlabel = bwlabel(subimg);  if max(max(imlabel))>1 % 說明有雜點  stats = regionprops(imlabel,'Area');  area = cat(1,stats.Area);  maxindex = find(area == max(area));  area(maxindex) = 0;    secondindex = find(area == max(area));   imindex = ismember(imlabel,secondindex);  subimg(imindex==1)=0;%去掉第二大連通域  end  subimgs = [subimgs;subimg]; end codes = []; for ii = 0:3  region = [ii*20+1,1,19,20];  subimg = imcrop(img,region);  minwidth = 20;  for angle = -60:60  imgr=imrotate(subimg,angle,'bilinear','crop');%crop 避免圖像大小變化  imlabel = bwlabel(imgr);  stats = regionprops(imlabel,'Area');  area = cat(1,stats.Area);  maxindex = find(area == max(area));  imindex = ismember(imlabel,maxindex);%最大連通域為1  [y,x] = find(imindex==1);  width = max(x)-min(x)+1;  if width<minwidth   minwidth = width;   imgrr = imgr;  end  end  mindiffv = 1000000;  for jj = 1:length(DIRS1)  imgsample = imread(strcat(samples,DIRS1(jj).name ));  imgsample = im2bw(imgsample);  diffv = abs(imgsample-imgrr);  alldiffv = sum(sum(diffv));  if alldiffv<mindiffv   mindiffv = alldiffv;   code = DIRS1(jj).name;   code = code(1);  end  end  codes = [codes,code]; end fprintf('驗證碼測試字符:%s/n',codes); num = codes-realcodes; num = length(find(num~=0)); singleerror = singleerror + num; if num>0  uniterror = uniterror +1; end fprintf('錯誤個數(shù):%d/n',num); endendfprintf('/n-----結(jié)果統(tǒng)計如下-----/n/n');fprintf('測試驗證碼的字符數(shù)量:%d/n',n*4);fprintf('測試驗證碼的字符錯誤數(shù)量:%d/n',singleerror);fprintf('單個字符識別正確率:%.2f%%/n',(1-singleerror/(n*4))*100);fprintf('測試驗證碼圖的數(shù)量:%d/n',n);fprintf('測試驗證碼圖的錯誤數(shù)量:%d/n',uniterror);fprintf('填對驗證碼的概率:%.2f%%/n',(1-uniterror/n)*100);