baca.py
Raw Download

# Sumber: https://github.com/YukaLangbuana/KTP-OCR
# sudo apt install tesseract-ocr-ind
# ~/env/bin/pip install PyTesseract opencv-python
import sys
from cv2 import (
    imread,
    threshold,
    cvtColor,
    COLOR_BGR2GRAY,
    THRESH_TRUNC,
    )
from pytesseract import image_to_string


filename = sys.argv[1]
img = imread(filename)

gray = cvtColor(img, COLOR_BGR2GRAY)
th, threshed = threshold(gray, 127, 255, THRESH_TRUNC)
s = image_to_string((threshed), lang='ind')
for line in s.splitlines():
    print([line])