def classify_single_image(model, image_path):
    try:
        # Read and preprocess the image
        image = cv2.imread(image_path)
        if image is None:
            return None, "Could not load image"

        # Make a copy for display
        display_image = copy.deepcopy(image)

        # Preprocess the image
        image = cv2.resize(image, (CONST.IMG_SIZE, CONST.IMG_SIZE))
        image = image.astype('float32') / 255.0  # Normalize to [0,1] range
        image = np.expand_dims(image, axis=0)  # Add batch dimension

        # Make prediction
        pred = model.predict(image, verbose=0)
        class_idx = np.argmax(pred, axis=1)[0]
        confidence = float(pred[0][class_idx])

        # Map prediction to class name
        class_names = {0: 'Cat', 1: 'Dog'}
        prediction = class_names[class_idx]

        # Add text to image
        font = cv2.FONT_HERSHEY_SIMPLEX
        location = (20, 30)
        fontScale = 0.8
        fontColor = (0, 255, 0)  # Green
        lineType = 2

        text = f"{prediction}: {confidence:.2%}"
        cv2.putText(display_image, text, location, font, fontScale, fontColor, lineType)

        # Save the annotated image
        output_path = "prediction_result.jpg"
        cv2.imwrite(output_path, display_image)

        return prediction, confidence, output_path

    except Exception as e:
        return None, f"Error during classification: {str(e)}"