ocr_engine.py

import easyocr
import numpy as np
import re
import cv2

reader = easyocr.Reader(['en'], gpu=False)

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

        # Preprocessing
        gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
        resized = cv2.resize(gray, None, fx=2.5, fy=2.5, interpolation=cv2.INTER_CUBIC)
        blurred = cv2.GaussianBlur(resized, (3, 3), 0)
        _, thresh = cv2.threshold(blurred, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

        # OCR
        result = reader.readtext(thresh, detail=0)
        combined_text = " ".join(result)
        print("OCR Result:", combined_text)

        # Improve regex to only match numbers with optional decimal
        match = re.search(r"\b(?:\d{1,3}\.?\d{1,2}|\d{1,4})\b", combined_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