python怎样辨认验证码【Python教程】,Python

在python爬虫爬取某些网站的验证码的时刻可能会碰到验证码辨认的题目，如今的验证码大多分为四类：1、盘算验证码2、滑块验证码3、识图验证码4、语音验证码

这里主假如辨认验证码，辨认的是简朴的验证码，要想让辨认率更高，辨认的越发正确就须要花许多的精神去练习本身的字体库。

辨认验证码一般是这几个步骤：

1、灰度处置惩罚

2、二值化

3、去除边框（假如有的话）

4、降噪

5、切割字符或许倾斜度改正

6、练习字体库

7、辨认

这6个步骤中前三个步骤是基础的，4或许5可根据实际情况挑选是不是须要，并不一定切割验证码，辨认率就会上升许多有时刻还会下落

用到的几个重要的python库： Pillow(python图象处置惩罚库)、OpenCV(高等图象处置惩罚库)、pytesseract(辨认库)

下面案例使用方法：

1、将要辨认的验证码图片放入与剧本同级的img文件夹中，建立out_img文件夹

2、python3 filename

3、二值化、降噪等各个阶段的图片将存储在out_img文件夹中，终究辨认效果会打印到屏幕上

完全的二维码辨认代码：

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):
  '''
  滋扰线降噪
  '''
  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,斑点个数
    :param x:
    :param y:
    :return:
    """
    filename =  './out_img/' + img_name.split('.')[0] + '-interferencePoint.jpg'
    # todo 推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:  # 左上极点,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:  # 右上极点
                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:  # 最上非极点,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:  # 左下极点
                # 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:  # 右下极点
                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:  # 最下非极点,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不在边境
            if x == 0:  # 左侧非极点
                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:  # 右侧非极点
                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:  # 具有9范畴前提的
                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):
  '''用行列和鸠合纪录遍历过的像素坐标替代纯真递归以处理cfs接见过深题目
  '''
  # 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  # 已接见过了
          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):
  '''搜刮区块出发点
  '''
  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[肇端，尽头]列表
  zoneHB=[]#各区块的Y轴[肇端，尽头]列表
  xmax=0#上一区块完毕斑点横坐标,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]
  # 辨认出的字符个数
  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)
      # 对图片举行滋扰线降噪
      im = interference_line(im,img_name)
      # 对图片举行点降噪
      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])
      # 假如有粘连字符，假如一个字符的长度太长就认为是粘连字符，并从中心举行切割
      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[肇端，尽头]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[肇端，尽头]位置
        im_position[2].insert(maxL_index + 1, im_position[2][maxL_index])
      # 切割字符，要想切得好就得设置参数，一般 1 or 2 就能够
      cutting_img(im,im_position,img_name,1,1)
      # 辨认验证码
      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)
          # 辨认验证码
          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('辨认为：%s' % str_img)
if __name__ == '__main__':
  main()

以上就是python怎样辨认验证码的细致内容，更多请关注ki4网别的相干文章！