Python用 KNN 进行验证码识别的实现方法

#-*- coding:UTF-8 -*-
import urllib,urllib2,cookielib,string,Image
def getchk(number):
 #创建cookie对象
 cookie = cookielib.LWPCookieJar()
 cookieSupport= urllib2.HTTPCookieProcessor(cookie)
 opener = urllib2.build_opener(cookieSupport, urllib2.HTTPHandler)
 urllib2.install_opener(opener)
 #首次与教务系统链接获得cookie#
 #伪装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  #请求头
 )
 # 捕捉http错误
 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   #请求头
 )
 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,'\'];
end
DIRS=dir([mydir,'*.jpg']); %扩展名
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);
 end
end

mydir='./bw/';
letter = './letter/';
if mydir(end)~='\'
 mydir=[mydir,'\'];
end
DIRS=dir([mydir,'*.jpg']); %扩展名
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;%颜色反转让字符成为联通域，方便去除噪点
 for ii = 0:3
  region = [ii*20+1,1,19,20];%把一张验证码分成四个20*20大小的字符图片
  subimg = imcrop(img,region);
  imlabel = bwlabel(subimg);
%  imshow(imlabel);
 
  if max(max(imlabel))>1 % 说明有噪点，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;%去掉第二大连通域，噪点不可能比字符大，所以第二大的就是噪点
  end
  name = strcat(letter,DIRS(i).name(1:length(DIRS(i).name)-4),'_',num2str(ii),'.jpg')
  imwrite(subimg,name);
 end
 end
end

if mydir(end)~='\'
 mydir=[mydir,'\'];
end
DIRS=dir([mydir,'*.jpg']); %扩展名
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 避免图像大小变化
  imlabel = bwlabel(imgr);
  stats = regionprops(imlabel,'Area');
  area = cat(1,stats.Area);
  maxindex = find(area == max(area));
  imindex = ismember(imlabel,maxindex);%最大连通域为1
  [y,x] = find(imindex==1);
  width = max(x)-min(x)+1;
  if width

mydir='./test/';
samples = './samples/';
if mydir(end)~='\'
 mydir=[mydir,'\'];
end
if samples(end)~='\'
 samples=[samples,'\'];
end
DIRS=dir([mydir,'*.jpg']); %扩展?
DIRS1=dir([samples,'*.jpg']); %扩展名
n=length(DIRS);%验证码总图数
singleerror = 0;%单个错误
uniterror = 0;%一张验证码错误个数
for i=1:n
 if ~DIRS(i).isdir
 realcodes = DIRS(i).name(1:4);
 fprintf('验证码实际字符:%s\n',realcodes);
 img = imread(strcat(mydir,DIRS(i).name ));
 img = rgb2gray(img);
 img = im2bw(img);
 img = 1-img;%颜色反转让字符成为联通域
 subimgs = [];
 for ii = 0:3
  region = [ii*20+1,1,19,20];%奇怪,为什么这样才能均分？
  subimg = imcrop(img,region);
  imlabel = bwlabel(subimg);
  if max(max(imlabel))>1 % 说明有杂点
  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;%去掉第二大连通域
  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 避免图像大小变化
  imlabel = bwlabel(imgr);
  stats = regionprops(imlabel,'Area');
  area = cat(1,stats.Area);
  maxindex = find(area == max(area));
  imindex = ismember(imlabel,maxindex);%最大连通域为1
  [y,x] = find(imindex==1);
  width = max(x)-min(x)+1;
  if width0
  uniterror = uniterror +1;
 end
 fprintf('错误个数:%d\n',num);
 end
end
fprintf('\n-----结果统计如下-----\n\n');
fprintf('测试验证码的字符数量:%d\n',n*4);
fprintf('测试验证码的字符错误数量:%d\n',singleerror);
fprintf('单个字符识别正确率:%.2f%%\n',(1-singleerror/(n*4))*100);
fprintf('测试验证码图的数量:%d\n',n);
fprintf('测试验证码图的错误数量:%d\n',uniterror);
fprintf('填对验证码的概率:%.2f%%\n',(1-uniterror/n)*100);