我们在网上浏览网页或注册账号时,会经常遇到验证码(CAPTCHA),如下图:
本文将具体介绍如何利用Python的图像处理模块pillow和OCR模块pytesseract来识别上述验证码(数字加字母)。
我们识别上述验证码的算法过程如下:
完整的Python代码如下:
# -*- coding:utf-8 -*-
import os,pytesseract
from PIL import Image
from collections import defaultdict
# tesseract.exe所在的文件路径
pytesseract.pytesseract.tesseract_cmd = r'D:\soft\tesseract-ocr\tesseract.exe'
# 获取图片中像素点数量最多的像素
def get_threshold(image):
pixel_dict = defaultdict(int)
# 像素及该像素出现次数的字典
rows, cols = image.size
# print('rows, cols:',rows, cols)
for i in range(rows):
for j in range(cols):
pixel = image.getpixel((i, j))#返回坐标处的pixel值
pixel_dict[pixel] += 1
# print('pixel_dict:',pixel_dict)
count_max = max(pixel_dict.values()) # 获取像素出现出多的次数
pixel_dict_reverse = {v:k for k,v in pixel_dict.items()}
threshold = pixel_dict_reverse[count_max] # 获取出现次数最多的像素点
return threshold
# 按照阈值进行二值化处理
# threshold: 像素阈值
def get_bin_table(threshold):
# 获取灰度转二值的映射table
table = []
for i in range(256):
rate = 0.1 # 在threshold的适当范围内进行处理
if threshold*(1-rate)<= i <= threshold*(1+rate):
table.append(1)
else:
table.append(0)
return table
# 去掉二值化处理后的图片中的噪声点
def cut_noise(image):
rows, cols = image.size # 图片的宽度和高度
change_pos = [] # 记录噪声点位置
# 遍历图片中的每个点,除掉边缘
for i in range(1, rows-1):
for j in range(1, cols-1):
# pixel_set用来记录该店附近的黑色像素的数量
pixel_set = []
# 取该点的邻域为以该点为中心的九宫格
for m in range(i-1, i+2):
for n in range(j-1, j+2):
if image.getpixel((m, n)) != 1: # 1为白色,0位黑色
pixel_set.append(image.getpixel((m, n)))
# 如果该位置的九宫内的黑色数量小于等于4,则判断为噪声
if len(pixel_set) <= 4:
change_pos.append((i,j))
# 对相应位置进行像素修改,将噪声处的像素置为1(白色)
for pos in change_pos:
image.putpixel(pos, 1)
return image # 返回修改后的图片
# 识别图片中的数字加字母
# 传入参数为图片路径,返回结果为:识别结果
def OCR_lmj(img_path):
image = Image.open(img_path) # 打开图片文件
imgry = image.convert('L') # 转化为灰度图
# 获取图片中的出现次数最多的像素,即为该图片的背景
max_pixel = get_threshold(imgry)
# 将图片进行二值化处理
table = get_bin_table(threshold=max_pixel)
out = imgry.point(table, '1')
# 去掉图片中的噪声(孤立点)
out = cut_noise(out)
#保存图片
out.save('./img_gray.jpg')
# 仅识别图片中的数字
#text = pytesseract.image_to_string(out, config='digits')
# 识别图片中的数字和字母
text = pytesseract.image_to_string(out)
# 去掉识别结果中的特殊字符
exclude_char_list = ' .:\\|\'\"?![],()~@#$%^&*_+-={};<>/¥'
text = ''.join([x for x in text if x not in exclude_char_list])
return text
def main():
# 识别指定文件目录下的图片
dir = '../captcha'
correct_count = 0 # 图片总数
total_count = 0 # 识别正确的图片数量
# 遍历figures下的png,jpg文件
for file in os.listdir(dir):
if file.endswith('.png') or file.endswith('.jpg'):
# print(file)
image_path = '%s/%s'%(dir,file) # 图片路径
answer = file.split('.')[0] # 图片名称,即图片中的正确文字
recognizition = OCR_lmj(image_path) # 图片识别的文字结果
print((answer, recognizition))
if recognizition == answer: # 如果识别结果正确,则total_count加1
correct_count += 1
total_count += 1
print('Total count: %d, correct: %d.'%(total_count, correct_count))
if __name__=='__main__':
# main()
# 单张图片识别
image_path = '2.jpg'
print(OCR_lmj(image_path))
# -*- coding:utf-8 -*-
from PIL import Image
from pytesseract import *
from fnmatch import fnmatch
from queue import Queue
import matplotlib.pyplot as plt
import cv2,time,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
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
'''
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 = './captcha'
for file in os.listdir(filedir):
if fnmatch(file, '*.jpg'):
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()