ocr.py

import pytesseract
import cv2

# Read the ID image into memory
image = cv2.imread("polo.jpg")

# Pre-process the image by converting it to grayscale and applying thresholding
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]

# Run OCR on the pre-processed image
text = pytesseract.image_to_string(thresh, lang="eng")

print(text)