When python crawler crawls the verification code of some websites, you may encounter the problem of verification code recognition. Most of the current verification codes are divided into four categories: 1. Calculate verification code 2. Slider verification code 3. Recognition Picture verification code 4, voice verification code
The main purpose here is to identify the verification code. What is recognized is a simple verification code. If you want to make the recognition rate higher, the recognition will be more accurate. It takes a lot of effort to train your own font library.
Identification of verification codes usually involves these steps:
1. Grayscale processing
2. Binarization
3. Remove borders (if If yes)
4. Noise reduction
5. Character cutting or tilt correction
6. Training font library
7. Recognition
The first three steps of these 6 steps are basic. You can choose whether 4 or 5 is needed according to the actual situation. The verification code does not necessarily need to be cut. The recognition rate will increase a lot and sometimes it will decrease.
Several main python libraries used: Pillow (python image processing library), OpenCV (advanced image processing library), pytesseract (recognition library)
The following case Usage:
1. Put the verification code image to be recognized into the img folder at the same level as the script, and create the out_img folder
2. python3 filename
3. Images at various stages such as binarization and noise reduction will be stored in the out_img folder, and the final recognition result will be printed on the screen.
Complete QR code identification code:
from PIL import Image
from pytesseract import *
from fnmatch import fnmatch
from queue import Queue
import matplotlib.pyplot as plt
import cv2
import time
import os
def clear_border(img,img_name):
'''去除边框
'''
filename = './out_img/' + img_name.split('.')[0] + '-clearBorder.jpg'
h, w = img.shape[:2]
for y in range(0, w):
for x in range(0, h):
# if y ==0 or y == w -1 or y == w - 2:
if y < 4 or y > w -4:
img[x, y] = 255
# if x == 0 or x == h - 1 or x == h - 2:
if x < 4 or x > h - 4:
img[x, y] = 255
cv2.imwrite(filename,img)
return img
def interference_line(img, img_name):
'''
干扰线降噪
'''
filename = './out_img/' + img_name.split('.')[0] + '-interferenceline.jpg'
h, w = img.shape[:2]
# ！！！opencv矩阵点是反的
# img[1,2] 1:图片的高度，2：图片的宽度
for y in range(1, w - 1):
for x in range(1, h - 1):
count = 0
if img[x, y - 1] > 245:
count = count + 1
if img[x, y + 1] > 245:
count = count + 1
if img[x - 1, y] > 245:
count = count + 1
if img[x + 1, y] > 245:
count = count + 1
if count > 2:
img[x, y] = 255
cv2.imwrite(filename,img)
return img
def interference_point(img,img_name, x = 0, y = 0):
"""点降噪
9邻域框,以当前点为中心的田字框,黑点个数
:param x:
:param y:
:return:
"""
filename = './out_img/' + img_name.split('.')[0] + '-interferencePoint.jpg'
# todo 判断图片的长宽度下限
cur_pixel = img[x,y]# 当前像素点的值
height,width = img.shape[:2]
for y in range(0, width - 1):
for x in range(0, height - 1):
if y == 0: # 第一行
if x == 0: # 左上顶点,4邻域
# 中心点旁边3个点
sum = int(cur_pixel) \
+ int(img[x, y + 1]) \
+ int(img[x + 1, y]) \
+ int(img[x + 1, y + 1])
if sum <= 2 * 245:
img[x, y] = 0
elif x == height - 1: # 右上顶点
sum = int(cur_pixel) \
+ int(img[x, y + 1]) \
+ int(img[x - 1, y]) \
+ int(img[x - 1, y + 1])
if sum <= 2 * 245:
img[x, y] = 0
else: # 最上非顶点,6邻域
sum = int(img[x - 1, y]) \
+ int(img[x - 1, y + 1]) \
+ int(cur_pixel) \
+ int(img[x, y + 1]) \
+ int(img[x + 1, y]) \
+ int(img[x + 1, y + 1])
if sum <= 3 * 245:
img[x, y] = 0
elif y == width - 1: # 最下面一行
if x == 0: # 左下顶点
# 中心点旁边3个点
sum = int(cur_pixel) \
+ int(img[x + 1, y]) \
+ int(img[x + 1, y - 1]) \
+ int(img[x, y - 1])
if sum <= 2 * 245:
img[x, y] = 0
elif x == height - 1: # 右下顶点
sum = int(cur_pixel) \
+ int(img[x, y - 1]) \
+ int(img[x - 1, y]) \
+ int(img[x - 1, y - 1])
if sum <= 2 * 245:
img[x, y] = 0
else: # 最下非顶点,6邻域
sum = int(cur_pixel) \
+ int(img[x - 1, y]) \
+ int(img[x + 1, y]) \
+ int(img[x, y - 1]) \
+ int(img[x - 1, y - 1]) \
+ int(img[x + 1, y - 1])
if sum <= 3 * 245:
img[x, y] = 0
else: # y不在边界
if x == 0: # 左边非顶点
sum = int(img[x, y - 1]) \
+ int(cur_pixel) \
+ int(img[x, y + 1]) \
+ int(img[x + 1, y - 1]) \
+ int(img[x + 1, y]) \
+ int(img[x + 1, y + 1])
if sum <= 3 * 245:
img[x, y] = 0
elif x == height - 1: # 右边非顶点
sum = int(img[x, y - 1]) \
+ int(cur_pixel) \
+ int(img[x, y + 1]) \
+ int(img[x - 1, y - 1]) \
+ int(img[x - 1, y]) \
+ int(img[x - 1, y + 1])
if sum <= 3 * 245:
img[x, y] = 0
else: # 具备9领域条件的
sum = int(img[x - 1, y - 1]) \
+ int(img[x - 1, y]) \
+ int(img[x - 1, y + 1]) \
+ int(img[x, y - 1]) \
+ int(cur_pixel) \
+ int(img[x, y + 1]) \
+ int(img[x + 1, y - 1]) \
+ int(img[x + 1, y]) \
+ int(img[x + 1, y + 1])
if sum <= 4 * 245:
img[x, y] = 0
cv2.imwrite(filename,img)
return img
def _get_dynamic_binary_image(filedir, img_name):
'''
自适应阀值二值化
'''
filename = './out_img/' + img_name.split('.')[0] + '-binary.jpg'
img_name = filedir + '/' + img_name
print('.....' + img_name)
im = cv2.imread(img_name)
im = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
th1 = cv2.adaptiveThreshold(im, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 21, 1)
cv2.imwrite(filename,th1)
return th1
def _get_static_binary_image(img, threshold = 140):
'''
手动二值化
'''
img = Image.open(img)
img = img.convert('L')
pixdata = img.load()
w, h = img.size
for y in range(h):
for x in range(w):
if pixdata[x, y] < threshold:
pixdata[x, y] = 0
else:
pixdata[x, y] = 255
return img
def cfs(im,x_fd,y_fd):
'''用队列和集合记录遍历过的像素坐标代替单纯递归以解决cfs访问过深问题
'''
# print('**********')
xaxis=[]
yaxis=[]
visited =set()
q = Queue()
q.put((x_fd, y_fd))
visited.add((x_fd, y_fd))
offsets=[(1, 0), (0, 1), (-1, 0), (0, -1)]#四邻域
while not q.empty():
x,y=q.get()
for xoffset,yoffset in offsets:
x_neighbor,y_neighbor = x+xoffset,y+yoffset
if (x_neighbor,y_neighbor) in (visited):
continue # 已经访问过了
visited.add((x_neighbor, y_neighbor))
try:
if im[x_neighbor, y_neighbor] == 0:
xaxis.append(x_neighbor)
yaxis.append(y_neighbor)
q.put((x_neighbor,y_neighbor))
except IndexError:
pass
# print(xaxis)
if (len(xaxis) == 0 | len(yaxis) == 0):
xmax = x_fd + 1
xmin = x_fd
ymax = y_fd + 1
ymin = y_fd
else:
xmax = max(xaxis)
xmin = min(xaxis)
ymax = max(yaxis)
ymin = min(yaxis)
#ymin,ymax=sort(yaxis)
return ymax,ymin,xmax,xmin
def detectFgPix(im,xmax):
'''搜索区块起点
'''
h,w = im.shape[:2]
for y_fd in range(xmax+1,w):
for x_fd in range(h):
if im[x_fd,y_fd] == 0:
return x_fd,y_fd
def CFS(im):
'''切割字符位置
'''
zoneL=[]#各区块长度L列表
zoneWB=[]#各区块的X轴[起始，终点]列表
zoneHB=[]#各区块的Y轴[起始，终点]列表
xmax=0#上一区块结束黑点横坐标,这里是初始化
for i in range(10):
try:
x_fd,y_fd = detectFgPix(im,xmax)
# print(y_fd,x_fd)
xmax,xmin,ymax,ymin=cfs(im,x_fd,y_fd)
L = xmax - xmin
H = ymax - ymin
zoneL.append(L)
zoneWB.append([xmin,xmax])
zoneHB.append([ymin,ymax])
except TypeError:
return zoneL,zoneWB,zoneHB
return zoneL,zoneWB,zoneHB
def cutting_img(im,im_position,img,xoffset = 1,yoffset = 1):
filename = './out_img/' + img.split('.')[0]
# 识别出的字符个数
im_number = len(im_position[1])
# 切割字符
for i in range(im_number):
im_start_X = im_position[1][i][0] - xoffset
im_end_X = im_position[1][i][1] + xoffset
im_start_Y = im_position[2][i][0] - yoffset
im_end_Y = im_position[2][i][1] + yoffset
cropped = im[im_start_Y:im_end_Y, im_start_X:im_end_X]
cv2.imwrite(filename + '-cutting-' + str(i) + '.jpg',cropped)
def main():
filedir = './easy_img'
for file in os.listdir(filedir):
if fnmatch(file, '*.jpeg'):
img_name = file
# 自适应阈值二值化
im = _get_dynamic_binary_image(filedir, img_name)
# 去除边框
im = clear_border(im,img_name)
# 对图片进行干扰线降噪
im = interference_line(im,img_name)
# 对图片进行点降噪
im = interference_point(im,img_name)
# 切割的位置
im_position = CFS(im)
maxL = max(im_position[0])
minL = min(im_position[0])
# 如果有粘连字符，如果一个字符的长度过长就认为是粘连字符，并从中间进行切割
if(maxL > minL + minL * 0.7):
maxL_index = im_position[0].index(maxL)
minL_index = im_position[0].index(minL)
# 设置字符的宽度
im_position[0][maxL_index] = maxL // 2
im_position[0].insert(maxL_index + 1, maxL // 2)
# 设置字符X轴[起始，终点]位置
im_position[1][maxL_index][1] = im_position[1][maxL_index][0] + maxL // 2
im_position[1].insert(maxL_index + 1, [im_position[1][maxL_index][1] + 1, im_position[1][maxL_index][1] + 1 + maxL // 2])
# 设置字符的Y轴[起始，终点]位置
im_position[2].insert(maxL_index + 1, im_position[2][maxL_index])
# 切割字符，要想切得好就得配置参数，通常 1 or 2 就可以
cutting_img(im,im_position,img_name,1,1)
# 识别验证码
cutting_img_num = 0
for file in os.listdir('./out_img'):
str_img = ''
if fnmatch(file, '%s-cutting-*.jpg' % img_name.split('.')[0]):
cutting_img_num += 1
for i in range(cutting_img_num):
try:
file = './out_img/%s-cutting-%s.jpg' % (img_name.split('.')[0], i)
# 识别验证码
str_img = str_img + image_to_string(Image.open(file),lang = 'eng', config='-psm 10') #单个字符是10，一行文本是7
except Exception as err:
pass
print('切图：%s' % cutting_img_num)
print('识别为：%s' % str_img)
if __name__ == '__main__':
main()The above is the detailed content of How python recognizes verification code. For more information, please follow other related articles on the PHP Chinese website!
![[Web front-end] Node.js quick start](https://img.php.cn/upload/course/000/000/067/662b5d34ba7c0227.png)
