ocr_engine.py

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

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

def preprocess_image(image):
    # Convert to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)

    # Blur + Otsu thresholding
    blur = cv2.GaussianBlur(gray, (3, 3), 0)
    _, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

    return thresh

def extract_weight_from_image(pil_image):
    try:
        # Convert PIL image to OpenCV image
        image = np.array(pil_image.convert("RGB"))
        processed = preprocess_image(image)

        # OCR
        result = reader.readtext(processed)
        print("OCR Results:", result)  # for debugging

        weight = None
        confidence = 0.0

        for detection in result:
            text = detection[1]
            conf = detection[2]

            match = re.search(r"\b\d+(\.\d+)?\b", text)  # more flexible matching
            if match:
                weight = match.group()
                confidence = conf
                break

        if weight:
            return weight, round(confidence * 100, 2)
        else:
            return "No weight detected", 0.0

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