ocr_engine.py

import cv2
import pytesseract
import numpy as np
from PIL import Image

def extract_weight_from_image(pil_img):
    try:
        img = pil_img.convert("L")  # grayscale
        img = np.array(img)

        img = cv2.resize(img, None, fx=2, fy=2, interpolation=cv2.INTER_CUBIC)
        blur = cv2.GaussianBlur(img, (5, 5), 0)
        thresh = cv2.adaptiveThreshold(
            blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
            cv2.THRESH_BINARY_INV, 11, 2
        )

        config = r'--oem 3 --psm 6 -c tessedit_char_whitelist=0123456789.'
        text = pytesseract.image_to_string(thresh, config=config)

        print("🔍 OCR RAW OUTPUT:", repr(text))

        weight = ''.join(filter(lambda c: c in '0123456789.', text)).strip()
        confidence = 95 if weight else 0
        return weight, confidence

    except Exception as e:
        print("❌ OCR Exception:", str(e))
        return "", 0