opencv--tesseract文档扫描OCR识别（VScode实现）

.exe下载和环境配置参考博文

# https://digi.bib.uni-mannheim.de/tesseract/
# 配置环境变量如E:\Program Files (x86)\Tesseract-OCR
# tesseract -v进行测试
# tesseract XXX.png 得到结果 
# pip install pytesseract
# anaconda lib site-packges pytesseract pytesseract.py
# tesseract_cmd 修改为绝对路径即可
from PIL import Image
import pytesseract
import cv2
import os

preprocess = 'thresh' #thresh

image = cv2.imread('G:\jupyternoteBook_01\image-py\ocr\page.jpg')

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#接下来可以进行滤波操作或者二值化操作对比一下效果

if preprocess == "thresh":
    gray = cv2.threshold(gray, 0, 255,cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

if preprocess == "blur":
    gray = cv2.medianBlur(gray, 3)#中值滤波
    
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
    
text = pytesseract.image_to_string(Image.open(filename))
print(text)
os.remove(filename)




cv2.imshow("Image", image)
cv2.imshow("Output", gray)
cv2.waitKey(0)