ocr_engine.py

import easyocr
import numpy as np
import cv2
import re
import logging
from mmocr.utils.ocr import MMOCR

# Set up logging for debugging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Initialize OCR engines
easyocr_reader = easyocr.Reader(['en'], gpu=False)
try:
    mmocr_reader = MMOCR(det='DB_r18', recog='CRNN')
except:
    mmocr_reader = None
    logging.warning("MMOCR initialization failed, falling back to EasyOCR only")

def estimate_blur(img):
    """Estimate image blur using Laplacian variance"""
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    return cv2.Laplacian(gray, cv2.CV_64F).var()

def enhance_image(img):
    try:
        # Convert to grayscale
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

        # Bilateral filter for noise reduction while preserving edges
        denoised = cv2.bilateralFilter(gray, d=9, sigmaColor=75, sigmaSpace=75)

        # CLAHE for contrast enhancement
        clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
        contrast = clahe.apply(denoised)

        # Adaptive thresholding for uneven lighting
        thresh = cv2.adaptiveThreshold(contrast, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
                                      cv2.THRESH_BINARY, 11, 2)

        # Morphological operations to enhance text
        kernel = np.ones((3, 3), np.uint8)
        morphed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=1)

        # Sharpen image
        sharpen_kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]])
        sharpened = cv2.filter2D(morphed, -1, sharpen_kernel)

        # Dynamic resizing
        h, w = sharpened.shape
        target_size = 800  # Target max dimension for OCR
        scale_factor = min(target_size / max(h, w), 2.0) if max(h, w) < 300 else min(target_size / max(h, w), 1.0)
        if scale_factor != 1.0:
            sharpened = cv2.resize(sharpened, None, fx=scale_factor, fy=scale_factor, 
                                 interpolation=cv2.INTER_CUBIC if scale_factor > 1 else cv2.INTER_AREA)

        return sharpened
    except Exception as e:
        logging.error(f"Image enhancement failed: {str(e)}")
        return img  # Return original image as fallback

def extract_weight_from_image(pil_img):
    try:
        img = np.array(pil_img)
        img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)

        # Estimate blur to adjust confidence threshold
        blur_score = estimate_blur(img)
        conf_threshold = 0.3 if blur_score < 100 else 0.5  # Lower threshold for blurry images

        # Preprocess image
        processed = enhance_image(img)

        # Initialize results
        best_weight = None
        best_conf = 0.0

        # EasyOCR detection
        easyocr_results = easyocr_reader.readtext(processed, detail=1, paragraph=False)
        if not easyocr_results:  # Fallback to original image if no results
            easyocr_results = easyocr_reader.readtext(img, detail=1, paragraph=False)

        # MMOCR detection (if available)
        mmocr_results = []
        if mmocr_reader:
            try:
                mmocr_result = mmocr_reader.readtext(processed)
                mmocr_results = [(bbox, text, score) for bbox, text, score in mmocr_result]
            except:
                logging.warning("MMOCR processing failed, using EasyOCR results only")

        # Combine results
        all_results = easyocr_results + mmocr_results

        for (bbox, text, conf) in all_results:
            original_text = text
            text = text.lower().strip()

            # Fix common OCR errors
            text = text.replace(",", ".").replace(";", ".")
            text = text.replace("o", "0").replace("O", "0")
            text = text.replace("s", "5").replace("S", "5")
            text = text.replace("g", "9").replace("G", "6")
            text = text.replace("l", "1").replace("I", "1")
            text = text.replace("b", "8").replace("B", "8")
            text = text.replace("kgs", "").replace("kg", "").replace("k9", "").replace("k", "")
            text = re.sub(r"[^\d\.]", "", text)

            # Stricter regex for weight (0.0 to 9999.999)
            if re.fullmatch(r"\d{1,4}(\.\d{0,3})?", text):
                if conf > best_conf and conf > conf_threshold:
                    best_weight = text
                    best_conf = conf

        if not best_weight:
            logging.info("No valid weight detected")
            return "Not detected", 0.0

        # Format output
        if "." in best_weight:
            int_part, dec_part = best_weight.split(".")
            int_part = int_part.lstrip("0") or "0"
            best_weight = f"{int_part}.{dec_part.rstrip('0')}"
        else:
            best_weight = best_weight.lstrip("0") or "0"

        return best_weight, round(best_conf * 100, 2)

    except Exception as e:
        logging.error(f"Weight extraction failed: {str(e)}")
        return "Not detected", 0.0