python 识别验证码

具体学习可去这个网址：点击打开链接

# __author__ = 'youngkl'
# -*- coding: utf-8 -*-

from PIL import  Image
import hashlib
import time
import os
import math

class VectorCompare:
    def magnitude(self,concordance):
        total=0
        for word,count in concordance.iteritems():
            total+=count**2 # count的平方
        return math.sqrt(total)

    def relation(self,concordance1,concordance2):
        relevance=0
        topvalue=0
        for word,count in concordance1.iteritems():
            if concordance2.has_key(word):
                topvalue+=count*concordance2[word]
        return topvalue/(self.magnitude(concordance1)*self.magnitude(concordance2))


def buildvector(im):
    d1={}
    count=0
    for i in im.getdata():
        d1[count]=i
        count+=1

    return d1

v=VectorCompare()

iconset = ['0','1','2','3','4','5','6','7','8','9','0','a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z']

imageset=[]


for letter in iconset:
    for img in os.listdir('./iconset/%s/'%(letter)):
        temp=[]
        if img!="Thumbs.db" and img!=".DS_Store" :
            temp.append(buildvector(Image.open("./iconset/%s/%s"%(letter,img))))
        imageset.append({letter:temp})


im=Image.open("ValidateCode (2).jpg")
im2=Image.new("L",im.size,255)
im=im.convert("L")
temp={}

for x in range(im.size[1]):
    for y in range(im.size[0]):
        pix=im.getpixel((y,x))
        if pix>130:
            pix=0
        else:
            pix=255
        # if pix == 236 : # these are the numbers to get
        im2.putpixel((y,x),pix)
        # temp[pix]=pix
        # if pix==0 :
        #     im2.putpixel((y,x),0)
im2.show()

inletter=False
foundLetter=False
start=0
end=0
letters=[]

for y in range(im2.size[0]):
    for x in range(im2.size[1]):
        pix=im2.getpixel((y,x))
        # print pix
        if pix!=0:
            inletter=True

    if foundLetter==False and inletter==True:
        foundLetter=True
        start=y

    if foundLetter==True and inletter==False:
        foundLetter=False
        end=y
        letters.append((start,end))
    inletter=False

print letters
count=0
for letter in letters:
    m=hashlib.md5()
    im3=im2.crop((letter[0],0,letter[1],im2.size[1]))

    guess=[]

    for image in imageset:
        for x,y in image.iteritems():
            if len(y)!=0:
                guess.append((v.relation(y[0],buildvector(im3)),x))

    guess.sort(reverse=True)
    print "",guess[0]
    count+=1

但是目前会有一个问题 现在的验证码不再是普通的单色验证码 如果有多种颜色干扰应该怎么处理

如果图像后面有个干扰的条纹就会对字符切割产生问题 这个应该怎么处理。。。