ocr_engine.py

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

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

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

        # Resize and enhance
        gray = cv2.resize(gray, None, fx=4, fy=4, interpolation=cv2.INTER_LINEAR)
        gray = cv2.GaussianBlur(gray, (3, 3), 0)
        gray = cv2.equalizeHist(gray)

        # Threshold
        _, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

        # Invert if dark background
        if np.mean(thresh > 127) < 0.5:
            thresh = cv2.bitwise_not(thresh)

        # OCR using Tesseract
        config = "--psm 6 -c tessedit_char_whitelist=0123456789."
        text = pytesseract.image_to_string(thresh, config=config)
        print("🔍 OCR Text:", text)

        # Extract weight
        match = re.search(r"\d{1,3}(?:\.\d{1,2})?", text)
        if match:
            weight = match.group()
            return f"{weight} kg", 100.0
        else:
            return "No weight detected kg", 0.0

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