简单实用的基于python的中文OCR字符识别

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import pytesseract
from PIL import Image

# open image
image = Image.open（‘2.jpg‘）
code = pytesseract.image_to_string（image lang=‘chi_sim‘）
print（code）

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

    ..A..H.     24064  2018-09-29 09:51  PythonApplication4code.vsPythonApplication4v14.suo

     文件      27754  2018-09-29 09:19  PythonApplication4codePythonApplication42.jpg

     文件        209  2018-09-29 08:54  PythonApplication4codePythonApplication4PythonApplication4.py

     文件       2028  2018-09-29 09:46  PythonApplication4codePythonApplication4PythonApplication4.pyproj

     文件        719  2018-09-29 09:26  PythonApplication4codePythonApplication4
equirements.txt

     文件        857  2018-09-29 08:48  PythonApplication4codePythonApplication4.sln

     文件   34344744  2018-09-29 08:58  PythonApplication4安装包 esseract-ocr-w64-setup-v4.0.0-beta.1.20180608.exe

     目录          0  2018-09-29 08:48  PythonApplication4code.vsPythonApplication4v14

     目录          0  2018-09-29 08:48  PythonApplication4code.vsPythonApplication4

    ...D.H.         0  2018-09-29 08:48  PythonApplication4code.vs

     目录          0  2018-09-29 09:26  PythonApplication4codePythonApplication4

     目录          0  2018-09-29 09:51  PythonApplication4code

     目录          0  2018-09-29 09:51  PythonApplication4安装包

     目录          0  2018-09-29 09:51  PythonApplication4

----------- ---------  ---------- -----  ----

             34400375                    14