Python 建立一个模型来识别验证码成功率

#!C:/Python27 #coding=utf-8 """ 1、截屏,获取验证码图片； 2、裁剪验证码为4个小图片； 3、把4张图片放大为255*255像素图 4、拿每块小图片去模型目录找相似的图片*4次； 5、组装成字符串--->4位验证码 """ import os ,sys import fnmatch import re,time import pytesseract from pytesser import * from PIL import Image,ImageDraw import urllib,random def GetVerficode(): #下载验证码图片 j = 1000 for i in range(1,2): url = 'https://ssom-cas.sfbest.com/cas/vcode?a=0.9529792121745766' print "download", i file("./code/%d.jpg" % j, "wb").write(urllib.urlopen(url).read()) j += 1 def GetImg(): ImgPath = (".//code//9911.jpg") def CutCrop():#分隔验证图片 """global data 全局变量在整个函数中有效""" ImgPath = (".//code//") j = 1000 for f in os.listdir(ImgPath): if f.endswith(".jpg"): print f img = Image.open(ImgPath+f).convert('L') print img.size w, h = img.size #rowheight = h // rownum #colwidth = w // colnum #imgry.show() for i in range(4): x = 10 + i*24 #验证码的x,y坐标 10+i*24 y=6 (x-4, y,x+6, y+14) y = 8 img.crop((x-4, y,x+8, y+14)).save("font/%d.bmp" % j) print "j=",j j += 1 def fixed_size(): """按照固定尺寸放大处理4图片""" dirpath =(".//font//") dirSave =(".//BigImg//") j = 10000 for imgfile in os.listdir(dirpath): print imgfile im = Image.open(dirpath+imgfile) #im.show() size = (256, 256) im2 =im.resize(size).convert('RGB') out = im2.resize(size,Image.ANTIALIAS) out.save(dirSave+'%d.bmp' % j) print u"\n按固定尺寸放大*4张图片,处理已完成" j += 1 """对比图片方法开始""" def getGray(image_file): tmpls=[] for h in range(0, image_file.size[1]):#h for w in range(0, image_file.size[0]):#w tmpls.append( image_file.getpixel((w,h)) ) return tmpls def getAvg(ls):#获取平均灰度值 return sum(ls)/len(ls) def getMH(a,b):#比较100个字符有几个字符相同 dist = 0; for i in range(0,len(a)): if a[i]==b[i]: dist=dist+1 return dist def getImgHash(fne): image_file = Image.open(fne) # 打开 image_file=image_file.resize((12, 12))#重置图片大小我12px X 12px image_file=image_file.convert("L")#转256灰度图 Grayls=getGray(image_file)#灰度集合 avg=getAvg(Grayls)#灰度平均值 bitls=''#接收获取0或1 #除去变宽1px遍历像素 for h in range(1, image_file.size[1]-1):#h for w in range(1, image_file.size[0]-1):#w if image_file.getpixel((w,h))>=avg:#像素的值比较平均值 大于记为1 小于记为0 bitls=bitls+'1' else: bitls=bitls+'0' return bitls ''''' m2 = hashlib.md5() m2.update(bitls) print m2.hexdigest(),bitls return m2.hexdigest() ''' """对比图片方法结束""" def FindImg(): """ 遍历Pic 目录下的图片,去路径中找图片后缀为PNG的图片,对比 """ file_dir = (".\\BigImg") L=[] for root,dirs,files in os.walk(file_dir): #print root,dirs,files #路径地址、文件夹名、文件名 for file in files: L.append(os.path.join(root,file)) #if imgfile.endswith(".bmp"): file_dir = (".\\result") M=[] for root, dirs, files in os.walk(file_dir): for file in files: if os.path.splitext(file)[1] == '.bmp': #print os.path.join(root, file) im2 = Image.open(os.path.join(root, file)) #im2.show() M.append(os.path.join(root, file)) #print M """外层循环4次,内层循环多次""" listcode = [] strtt = "" for i in L : print "\n",i ,"\n" a=getImgHash(i) PreMax = {} Listcom = [] for j in M: #im2 = Image.open(j) #print j b=getImgHash(j) compare=getMH(a,b) print j,u'相似度',str(compare) PreMax.setdefault(str(compare),j) Listcom.append(compare) #取出最大百分比的值，再通过最大值取拿到Key,再获取图片名称 print u"\n各图片的相似度及图片路径:\n",PreMax,"\n" print "\n所有相似度的百分值集合:\n",Listcom,"\n" """取出最相似的""" a = max(Listcom) """拿到最相似的图片路径""" strpath = PreMax.get(str(a),j) """截取字符串11-12位""" name = strpath[11:12] strtt += name #name = strpath[strpath.rfind("/")+12:strpath.rfind(".")]#截取12位到.的字符串 listcode.append(name) print "\n",listcode,"\n" print strtt """下载图片""" GetVerficode() """裁剪图片""" CutCrop() """放大图片""" fixed_size() """对比图片""" FindImg()