OpenCV---数字验证码识别
推文:Python验证码识别 安装Pillow、tesseract-ocr与pytesseract模块的安装以及错误解决
一:依赖环境安装
pip install Pillow
pip3 install pytesseract
二:安装tesseract-ocr
(一)介绍
其中pytesseract会直接调用tesseract模块,我们需要进行安装
不然可会报错
pytesseract.TesseractNotFoundError: tesseract is not installed or it's not in your path
(二)下载地址
github地址: https://github.com/tesseract-ocr/tesseract
(三)下载traineddata训练数据
github地址:https://github.com/tesseract-ocr/tessdata
注意:我们还是要将其设置环境变量
pytesseract.TesseractError: (1, 'Error opening data file \\OtherEnv\\tesseract-Win32\\tessdata/eng.traineddata Please make sure the TESSDATA_PREFIX environment variable is set to the parent directory of your "tessdata" directory. Failed loading language \'eng\' Tesseract couldn\'t load any languages! Could not initialize tesseract.')
现在我们重新启用cmd命令行,可以在cmd命令行调用python文件,获取到验证数据
但是我们在PyCharm中使用时还是需要修改python文件
还有在我们的程序文件中加入环境变量
os.environ['TESSDATA_PREFIX'] = "C:/OtherEnv/tesseract-Win32/tessdata"
三:代码实现
import cv2 as cv import numpy as np from PIL import Image import os import pytesseract as tess os.environ['TESSDATA_PREFIX'] = "C:/OtherEnv/tesseract-Win32/tessdata" def recognize_text(image): gray = cv.cvtColor(image,cv.COLOR_BGR2GRAY) ret,binary = cv.threshold(gray,0,255,cv.THRESH_BINARY_INV|cv.THRESH_OTSU) kernel = cv.getStructuringElement(cv.MORPH_RECT,(1,2)) mid1 = cv.morphologyEx(binary,cv.MORPH_OPEN,kernel) kernel = cv.getStructuringElement(cv.MORPH_RECT, (2,1)) open_out = cv.morphologyEx(mid1, cv.MORPH_OPEN, kernel) cv.imshow("bin1",open_out) cv.bitwise_not(open_out,open_out) #变白色背景 textImage = Image.fromarray(open_out) text = tess.image_to_string(textImage) print("result:%s"%text) src = cv.imread("./y4.png") #读取图片 cv.namedWindow("input image",cv.WINDOW_AUTOSIZE) #创建GUI窗口,形式为自适应 cv.imshow("input image",src) #通过名字将图像和窗口联系 recognize_text(src) cv.waitKey(0) #等待用户操作,里面等待参数是毫秒,我们填写0,代表是永远,等待用户操作 cv.destroyAllWindows() #销毁所有窗口