# Compute mean and std from the TRAINING set only — never from validation or test
def compute_train_stats(train_dir, sample_limit=1000):
    """Compute pixel mean and std across the training set."""
    pixel_values = []
    count = 0
    for class_name in os.listdir(train_dir):
        class_path = os.path.join(train_dir, class_name)
        for fname in os.listdir(class_path):
            if count >= sample_limit:
                break
            img = cv2.imread(os.path.join(class_path, fname), cv2.IMREAD_GRAYSCALE)
            if img is not None:
                pixel_values.append(img.astype(np.float32).flatten() / 255.0)
                count += 1
    pixels = np.concatenate(pixel_values)
    return pixels.mean(), pixels.std()

train_mean, train_std = compute_train_stats(TRAIN_DIR)
image_normalized = (image_scaled - train_mean) / train_std