1. First prepare the environment:
python Version: 2.7 / 3.6
Operating System: windows system
2. Preparation Tool:
tesseract-ocr (Baidu network disk address: https: //pan.baidu.com/s/1OL0g1MBzeijD23JN0UGC0Q)
Pycharm (Download: http: //www.jetbrains.com/pycharm/download/#section=windows)
3. Install the python-related packages (used by the author is py2.7)
pip install Pillow
pip install pytesseract
4. tesseract-ocr and associating the python, so python can call Tesseract-OCR program identification codes / Text:
C:\python27\Lib\site-packages\pytesseract\pytesseract.py
Modifying the first document pytesseract.py tesseract_cmd 24 rows of point Tesseract-OCR tesseract.exe
Original content:
Modified content:
Note: Be sure to pay attention to the novice / and \ distinction
5. Open Pycharm writing process:
The need to tell the novice aaa.jpg which is stored in the directory py script, lang = 'chi_sim' on behalf of Chinese recognize, if not not recognize Chinese
6. Run the script can see the results
Special note: If the steps exactly right, but the operation error, please uninstall pytesseract reinstall the problem will be solved (uninstall command pip uninstall pytesseract)