Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from ultralytics import YOLO | |
| import cv2 | |
| import spaces | |
| import numpy as np | |
| import fitz # PyMuPDF | |
| from PIL import Image | |
| # Load the trained model | |
| model_path = 'runs/detect/train7/weights/best.pt' # Replace with the path to your trained .pt file | |
| model = YOLO(model_path) | |
| # Define the class indices for figures and tables | |
| figure_class_index = 3 # class index for figures | |
| table_class_index = 4 # class index for tables | |
| # Function to perform inference on an image and return bounding boxes for figures and tables | |
| def infer_image_and_get_boxes(image, confidence_threshold=0.6): | |
| results = model(image) | |
| boxes = [ | |
| (int(box.xyxy[0][0]), int(box.xyxy[0][1]), int(box.xyxy[0][2]), int(box.xyxy[0][3])) | |
| for result in results for box in result.boxes | |
| if int(box.cls[0]) in {figure_class_index, table_class_index} and box.conf[0] > confidence_threshold | |
| ] | |
| return boxes | |
| # Function to crop images from the boxes | |
| def crop_images_from_boxes(image, boxes, scale_factor): | |
| cropped_images = [ | |
| image[int(y1 * scale_factor):int(y2 * scale_factor), int(x1 * scale_factor):int(x2 * scale_factor)] | |
| for (x1, y1, x2, y2) in boxes | |
| ] | |
| return cropped_images | |
| def process_pdf(pdf_file): | |
| # Open the PDF file | |
| doc = fitz.open(pdf_file) | |
| all_cropped_images = [] | |
| # Set the DPI for inference and high resolution for cropping | |
| low_dpi = 50 | |
| high_dpi = 300 | |
| # Calculate the scaling factor | |
| scale_factor = high_dpi / low_dpi | |
| # Loop through each page | |
| for page_num in range(len(doc)): | |
| page = doc.load_page(page_num) | |
| # Perform inference at low DPI | |
| low_res_pix = page.get_pixmap(dpi=low_dpi) | |
| low_res_img = np.frombuffer(low_res_pix.samples, dtype=np.uint8).reshape(low_res_pix.height, low_res_pix.width, 3) | |
| # Get bounding boxes from low DPI image | |
| boxes = infer_image_and_get_boxes(low_res_img) | |
| if boxes: | |
| # Load high DPI image for cropping only if boxes are found | |
| high_res_pix = page.get_pixmap(dpi=high_dpi) | |
| high_res_img = np.frombuffer(high_res_pix.samples, dtype=np.uint8).reshape(high_res_pix.height, high_res_pix.width, 3) | |
| # Crop images at high DPI | |
| cropped_imgs = crop_images_from_boxes(high_res_img, boxes, scale_factor) | |
| all_cropped_images.extend(cropped_imgs) | |
| return all_cropped_images | |
| # Create Gradio interface | |
| iface = gr.Interface( | |
| fn=process_pdf, | |
| inputs=gr.File(label="Upload a PDF"), | |
| outputs=gr.Gallery(label="Cropped Figures and Tables from PDF Pages"), | |
| title="Fast document layout analysis based on YOLOv8", | |
| description="Upload a PDF file to get cropped figures and tables from each page." | |
| ) | |
| # Launch the app | |
| iface.launch() | |