ocr_engine.py

import numpy as np
import re
import cv2
import pytesseract

def extract_weight_from_image(pil_img):
    try:
        img = np.array(pil_img)

        # Convert to grayscale
        gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

        # Resize (sharpens small digits)
        gray = cv2.resize(gray, None, fx=2.5, fy=2.5, interpolation=cv2.INTER_CUBIC)

        # Thresholding to clean up image
        _, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

        # Run Tesseract OCR
        custom_config = r'--oem 3 --psm 6'
        text = pytesseract.image_to_string(thresh, config=custom_config)
        print("OCR Text:", text)

        # Extract weight pattern like 25.50 or 150
        match = re.search(r"\b\d{1,4}\.?\d{0,2}\b", text)
        if match:
            return match.group(), 95.0
        else:
            return "No weight detected", 0.0

    except Exception as e:
        return f"Error: {str(e)}", 0.0