import io import base64 import numpy as np from PIL import Image from ultralytics import YOLO from utils.predict_bounding_boxes import predict_bounding_boxes from utils.manga_ocr_utils import get_text_from_image from utils.translate_manga import translate_manga from utils.process_contour import process_contour from utils.write_text_on_image import add_text MODEL_PATH = "./model_creation/runs/detect/train5/weights/best.pt" object_detection_model = YOLO(MODEL_PATH) def extract_text_from_regions(image: np.ndarray, results: list): for result in results: x1, y1, x2, y2, _, _ = result detected_image = image[int(y1):int(y2), int(x1):int(x2)] if detected_image.shape[-1] == 4: detected_image = detected_image[:, :, :3] im = Image.fromarray(np.uint8(detected_image * 255)) text = get_text_from_image(im) processed_image, cont = process_contour(detected_image) translated_text = translate_manga(text, source_lang="auto", target_lang="en") add_text(processed_image, translated_text, cont) def convert_image_to_base64(image: Image.Image) -> str: buff = io.BytesIO() image.save(buff, format="PNG") return base64.b64encode(buff.getvalue()).decode("utf-8") def predict(image: np.ndarray): image = Image.fromarray(image) image.save("image.png") try: np_image = np.array(image) results = predict_bounding_boxes(object_detection_model, "image.png") extract_text_from_regions(np_image, results) return np_image except Exception as e: print(f"Error: {str(e)}") return None