python 验证码处理

一、

灰度处理，就是把彩色的验证码图片转为灰色的图片。

二值化，是将图片处理为只有黑白两色的图片，利于后面的图像处理和识别

   # 自适应阀值二值化
   def _get_dynamic_binary_image(filedir, img_name):
       filename =   './out_img/' + img_name.split('.')[0] + '-binary.jpg'
       img_name = filedir + '/' + img_name
       print('.....' + img_name)
       im =dz.imread(img_name)
       im = dz.cvtColor(im,dz.COLOR_BGR2GRAY) #灰值化
       # 二值化
       th1 = dz.adaptiveThreshold(im, 255, dz.ADAPTIVE_THRESH_GAUSSIAN_C, dz.THRESH_BINARY, 21, 1)

      dz.imwrite(filename,th1)
      return th1

二、去除边框

 # 去除边框
 def clear_border(img,img_name):
   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 < 2 or y > w - 2:
         img[x, y] = 255
       if x < 2 or x > h -2:
         img[x, y] = 255

   cv2.imwrite(filename,img)
   return img

在用OpenCV时，图片的矩阵点是反的，就是长和宽是颠倒的

三、降噪

降噪是验证码处理中比较重要的一个步骤，我这里使用了点降噪和线降噪，，，只能去除细的干扰线

 # 干扰线降噪
 def interference_line(img, img_name):
     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

 # 点降噪
 def interference_point(img,img_name, x = 0, y = 0):
     """
     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

五、字符切割

 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

切割粘连字符代码

       # 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

切割粘连字符代码

 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)

六、识别：

识别用的是typesseract库，主要识别一行字符和单个字符时的参数设置，识别中英文的参数设置，代码很简单就一行，我这里大多是filter文件的操作

       # 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)
           # 识别字符
           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