某个招聘网站的验证码识别,过程如下
一: 原始验证码:
二: 首先对验证码进行分析,该验证码的数字颜色有变化,这个就是识别这个验证码遇到的比较难的问题,解决方法是使用PIL 中的 getpixel 方法进行变色处理,统一把非黑色的像素点变成黑色
变色后的图片
三: 通过观察,发现该验证码有折线,需要对图片进行降噪处理。
降噪后的图片
四:识别:
这里只是简单的使用 pytesseract 模块进行识别
识别结果如下:
总共十一个验证码,识别出来了9个,综合识别率是百分之八十。
总结:验证码识别只是简单调用了一下Python的第三方库,本验证码的识别难点如果给带颜色的数字变色。
下面是代码:
二值化变色:
#-*-coding:utf-8-*- from PIL import Imagedef test(path):img=Image.open(path)w,h=img.sizefor x in range(w):for y in range(h):r,g,b=img.getpixel((x,y))if 190<=r<=255 and 170<=g<=255 and 0<=b<=140:img.putpixel((x,y),(0,0,0))if 0<=r<=90 and 210<=g<=255 and 0<=b<=90:img.putpixel((x,y),(0,0,0))img=img.convert('L').point([0]*150+[1]*(256-150),'1')return imgfor i in range(1,13):path = str(i) + '.jpg'im = test(path)path = path.replace('jpg','png')im.save(path)
二:降噪
#-*-coding:utf-8-*-# coding:utf-8 import sys, os from PIL import Image, ImageDraw# 二值数组 t2val = {}def twoValue(image, G):for y in xrange(0, image.size[1]):for x in xrange(0, image.size[0]):g = image.getpixel((x, y))if g > G:t2val[(x, y)] = 1else:t2val[(x, y)] = 0# 根据一个点A的RGB值,与周围的8个点的RBG值比较,设定一个值N(0 <N <8),当A的RGB值与周围8个点的RGB相等数小于N时,此点为噪点 # G: Integer 图像二值化阀值 # N: Integer 降噪率 0 <N <8 # Z: Integer 降噪次数 # 输出 # 0:降噪成功 # 1:降噪失败 def clearNoise(image, N, Z):for i in xrange(0, Z):t2val[(0, 0)] = 1t2val[(image.size[0] - 1, image.size[1] - 1)] = 1for x in xrange(1, image.size[0] - 1):for y in xrange(1, image.size[1] - 1):nearDots = 0L = t2val[(x, y)]if L == t2val[(x - 1, y - 1)]:nearDots += 1if L == t2val[(x - 1, y)]:nearDots += 1if L == t2val[(x - 1, y + 1)]:nearDots += 1if L == t2val[(x, y - 1)]:nearDots += 1if L == t2val[(x, y + 1)]:nearDots += 1if L == t2val[(x + 1, y - 1)]:nearDots += 1if L == t2val[(x + 1, y)]:nearDots += 1if L == t2val[(x + 1, y + 1)]:nearDots += 1if nearDots < N:t2val[(x, y)] = 1def saveImage(filename, size):image = Image.new("1", size)draw = ImageDraw.Draw(image)for x in xrange(0, size[0]):for y in xrange(0, size[1]):draw.point((x, y), t2val[(x, y)])image.save(filename) for i in range(1,12):path = str(i) + ".png"image = Image.open(path).convert("L")twoValue(image, 100)clearNoise(image, 3, 2)path1 = str(i) + ".jpeg"saveImage(path1, image.size)
三:识别
#-*-coding:utf-8-*-from PIL import Image import pytesseractdef recognize_captcha(img_path):im = Image.open(img_path)# threshold = 140# table = []# for i in range(256):# if i < threshold:# table.append(0)# else:# table.append(1)# # out = im.point(table, '1')num = pytesseract.image_to_string(im)return numif __name__ == '__main__':for i in range(1, 12):img_path = str(i) + ".jpeg"res = recognize_captcha(img_path)strs = res.split("\n")if len(strs) >=1:print (strs[0])