[python] Tesseract-ocr Example

How to implement OCR in pyhton. Advanced: Identify non-english text.

Environment & Software

• Python Lib: pytesseract https://pypi.org/project/pytesseract/
  pip install pytesseract
• Install the newest tesseract.
  https://github.com/UB-Mannheim/tesseract/tags
• Pre-trained language data
  https://github.com/tesseract-ocr/tessdata

Implement

Python code

from PIL import Image
import pytesseract

def main():
    pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe" # The path is defined by where you install the execute file.
    img = Image.open(r"image\testIMG.jpg") # Please change the image path to yours.
    #img.show()
    print(pytesseract.image_to_string(img, lang="eng"))

if __name__ == "__main__":
    main()

Languages

If you have non-english text to find, please search the pre-trained language set and download to your "Tessract" installed path -> tessdata folder.
There is only "eng.traineddata" by default.

Then modify the code:

from PIL import Image
import pytesseract
import cv2
from pytesseract import Output

def main():
    pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
    img = cv2.imread('test.png')
    # Assume we want to identify some Traditional Chinese text.
    text = pytesseract.image_to_string(img, lang='chi_tra+eng')
    prind(text)

if __name__ == "__main__":
    main()