清理圖片，對圖片進行二值化，去邊框，去干擾線，去點

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 osdef clear_border(img,img_name):'''去除邊框'''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] = 255return imgdef interference_line(img, img_name):'''干擾線降噪'''h, w = img.shape[:2]# ！！！opencv矩陣點是反的# img[1,2] 1:圖片的高度，2：圖片的寬度for r in range(0,2):for y in range(1, w - 1):for x in range(1, h - 1):count = 0if img[x, y - 1] > 245:count = count + 1if img[x, y + 1] > 245:count = count + 1if img[x - 1, y] > 245:count = count + 1if img[x + 1, y] > 245:count = count + 1if count > 2:img[x, y] = 255return imgdef interference_point(img,img_name, x = 0, y = 0):"""點降噪9鄰域框,以當前點為中心的田字框,黑點個數:param x::param y::return:"""# todo 判斷圖片的長寬度下限cur_pixel = img[x,y]# 當前像素點的值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: # 左上頂點,4鄰域# 中心點旁邊3個點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] = 0elif x == height - 1: # 右上頂點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] = 0else: # 最上非頂點,6鄰域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] = 0elif y == width - 1: # 最下面一行if x == 0: # 左下頂點# 中心點旁邊3個點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] = 0elif x == height - 1: # 右下頂點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] = 0else: # 最下非頂點,6鄰域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] = 0else: # y不在邊界if x == 0: # 左邊非頂點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] = 0elif x == height - 1: # 右邊非頂點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] = 0else: # 具備9領域條件的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] = 0return imgdef _get_dynamic_binary_image(filedir,img_name):'''自適應閥值二值化'''filename = './easy_code/' + img_name.split('.')[0] + '-binary.jpg'img_name = filedir + '/' + img_nameim = 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 th1def recognize():　　
filedir = './images'　　#驗證碼路徑for file in os.listdir(filedir):if fnmatch(file, '*.jpg'):img_name = file# 自適應閾值二值化im = _get_dynamic_binary_image(filedir,img_name)# 去除邊框im = clear_border(im,img_name)# 對圖片進行干擾線降噪im = interference_line(im,img_name)# 對圖片進行點降噪im = interference_point(im,img_name)filename = './easy_code/' + img_name.split('.')[0] + '-interferencePoint.jpg'　　#easy_code為保存路徑cv2.imwrite(filename,im)　　#保存圖片 recognize()

以上代碼改自 老板丶魚丸粗面 的 《python驗證碼識別》對于驗證碼識別大佬那還有跟詳細的介紹。

附鏈接：https://www.cnblogs.com/qqandfqr/p/7866650.html

轉載于:https://www.cnblogs.com/dfy-blog/p/11563331.html

總結

以上是生活随笔為你收集整理的Python爬虫笔记【一】模拟用户访问之验证码清理（4）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。