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何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 Image
def test(path):
img=Image.open(path)
w,h=img.size
for 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 img
for 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)] = 1
else:
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)] = 1
t2val[(image.size[0] - 1, image.size[1] - 1)] = 1
for x in xrange(1, image.size[0] - 1):
for y in xrange(1, image.size[1] - 1):
nearDots = 0
L = t2val[(x, y)]
if L == t2val[(x - 1, y - 1)]:
nearDots += 1
if L == t2val[(x - 1, y)]:
nearDots += 1
if L == t2val[(x - 1, y + 1)]:
nearDots += 1
if L == t2val[(x, y - 1)]:
nearDots += 1
if L == t2val[(x, y + 1)]:
nearDots += 1
if L == t2val[(x + 1, y - 1)]:
nearDots += 1
if L == t2val[(x + 1, y)]:
nearDots += 1
if L == t2val[(x + 1, y + 1)]:
nearDots += 1
if nearDots < N:
t2val[(x, y)] = 1
def 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 pytesseract
def 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 num
if __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])