ocr_engine.py

import easyocr
import numpy as np
import cv2
import re

# Initialize OCR reader once
reader = easyocr.Reader(['en'], gpu=False)

def extract_weight_from_image(pil_img):
    try:
        # Convert image to NumPy format
        img = np.array(pil_img)

        # Resize and preprocess
        img = cv2.resize(img, None, fx=3.5, fy=3.5, interpolation=cv2.INTER_LINEAR)
        gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
        gray = cv2.bilateralFilter(gray, 11, 17, 17)
        _, thresh = cv2.threshold(gray, 120, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)

        # OCR
        results = reader.readtext(thresh)

        # Debug
        print("OCR Results:", results)

        weight_candidates = []
        for _, text, conf in results:
            clean = text.lower().replace("kg", "").strip()
            clean = clean.replace("o", "0").replace("O", "0")  # fix OCR misreads

            # Match weights like 86, 85.5, 102.3
            if re.fullmatch(r"\d{2,4}(\.\d{1,2})?", clean):
                weight_candidates.append((clean, conf))

        if not weight_candidates:
            return "Not detected", 0.0

        # Return best candidate
        best_weight, best_conf = sorted(weight_candidates, key=lambda x: -x[1])[0]
        return best_weight, round(best_conf * 100, 2)

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