使用pytesseract时得先安装tesseract,tesseract-ocr和pytesseract
from PIL import Image from PIL import ImageEnhance import pytesseract import re # 如果报错加上下面两行代码,更改tesseract路径 pytesseract.pytesseract.tesseract_cmd = ‘D:\\Program Files\\Tesseract-OCR\\tesseract.exe‘ tessdata_dir_config = ‘--tessdata-dir "D:\\Program Files\\Tesseract-OCR\\tessdata"‘ im=Image.open("./img/10.jpg") im=im.convert(‘L‘) im.show() im=ImageEnhance.Contrast(im) im=im.enhance(1) #im = im.resize((300, 90)) ltext = pytesseract.image_to_string(im) #去掉非法字符,只保留字母数字 ltext = re.sub("\W", "", ltext) im.show() print(ltext) #print(pytesseract.image_to_string(im)) #print(pytesseract.image_to_boxes(im)) #print(im.format, im.size, im.mode)
原文:https://www.cnblogs.com/linyouyi/p/11427171.html