清理图片，对图片进行二值化，去边框，去干扰线，去点
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
''' 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 return img def interference_line(img, img_name):
'''
干扰线降噪
''' 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 r in range(0,2):
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 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:
"""
# 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 return img def _get_dynamic_binary_image(filedir,img_name):
'''
自适应阀值二值化
'''
filename = './easy_code/' + 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) return th1 def recognize():
filedir = './images' #验证码路径 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)
filename = './easy_code/' + img_name.split('.')[0] + '-interferencePoint.jpg' #easy_code为保存路径
cv2.imwrite(filename,im) #保存图片 recognize()
以上代码改自 老板丶鱼丸粗面 的 《python验证码识别》对于验证码识别大佬那还有跟详细的介绍。