app.py

import gradio as gr
from ultralytics import YOLO
import cv2
import numpy as np
from PIL import Image, ImageDraw, ImageFont
import base64
from io import BytesIO
import tempfile
import os
from pathlib import Path
import shutil

# Load YOLOv8 model
model = YOLO("best.pt")

# Create directories if not present
uploaded_folder = Path('Uploaded_Picture')
predicted_folder = Path('Predicted_Picture')
uploaded_folder.mkdir(parents=True, exist_ok=True)
predicted_folder.mkdir(parents=True, exist_ok=True)

# Path to store accumulated HTML data
html_file_path = Path(tempfile.gettempdir()) / 'patient_data.html'

# Function to predict image and add bounding box, text, circle, and watermark
def predict_image(input_image, name, age, medical_record, sex):
    if input_image is None:
        return None, "Please Input The Image"

    # Convert Gradio input image (PIL Image) to numpy array
    image_np = np.array(input_image)

    # Ensure the image is in the correct format
    if len(image_np.shape) == 2:  # grayscale to RGB
        image_np = cv2.cvtColor(image_np, cv2.COLOR_GRAY2RGB)
    elif image_np.shape[2] == 4:  # RGBA to RGB
        image_np = cv2.cvtColor(image_np, cv2.COLOR_RGBA2RGB)

    # Perform prediction
    results = model(image_np)

    # Draw bounding boxes on the image
    image_with_boxes = image_np.copy()
    raw_predictions = []

    if results[0].boxes:
        # Sort the results by confidence and take the highest confidence one
        highest_confidence_result = max(results[0].boxes, key=lambda x: x.conf.item())

        # Determine the label based on the class index
        class_index = highest_confidence_result.cls.item()
        if class_index == 0:
            label = "Immature"
            color = (0, 255, 255)  # Yellow for Immature
        elif class_index == 1:
            label = "Mature"
            color = (255, 0, 0)  # Red for Mature
        else:
            label = "Normal"
            color = (0, 255, 0)  # Green for Normal

        confidence = highest_confidence_result.conf.item()
        xmin, ymin, xmax, ymax = map(int, highest_confidence_result.xyxy[0])
        
        # Draw the bounding box
        cv2.rectangle(image_with_boxes, (xmin, ymin), (xmax, ymax), color, 2)

        # Calculate the center of the bounding box
        center_x = (xmin + xmax) // 2
        center_y = (ymin + ymax) // 2
        
        # Calculate the radius (1/12 of the average of the width and height of the bounding box)
        box_width = xmax - xmin
        box_height = ymax - ymin
        radius = int((box_width + box_height) / 24)  # Average of width and height divided by 12

        # Draw a white circle at the center of the bounding box
        cv2.circle(image_with_boxes, (center_x, center_y), radius, (255, 255, 255), thickness=2)
        
        # Enlarge font scale and thickness
        font_scale = 1.0
        thickness = 2
        
        # Calculate label background size
        (text_width, text_height), baseline = cv2.getTextSize(f'{label} {confidence:.2f}', cv2.FONT_HERSHEY_SIMPLEX, font_scale, thickness)
        cv2.rectangle(image_with_boxes, (xmin, ymin - text_height - baseline), (xmin + text_width, ymin), (0, 0, 0), cv2.FILLED)
        
        # Put the label text with black background
        cv2.putText(image_with_boxes, f'{label} {confidence:.2f}', (xmin, ymin - 10), cv2.FONT_HERSHEY_SIMPLEX, font_scale, (255, 255, 255), thickness)
        
        raw_predictions.append(f"Label: {label}, Confidence: {confidence:.2f}, Box: [{xmin}, {ymin}, {xmax}, {ymax}]")

    raw_predictions_str = "\n".join(raw_predictions)
    
    # Convert to PIL image for further processing
    pil_image_with_boxes = Image.fromarray(image_with_boxes)

    # Add text and watermark
    pil_image_with_boxes = add_text_and_watermark(pil_image_with_boxes, name, age, medical_record, sex, label)
    
    # Save images to directories
    image_name = f"{name}-{age}-{sex}-{medical_record}.png"
    input_image.save(uploaded_folder / image_name)
    pil_image_with_boxes.save(predicted_folder / image_name)
    
    return pil_image_with_boxes, raw_predictions_str

# Function to add watermark
def add_watermark(image):
    try:
        logo = Image.open('image-logo.png').convert("RGBA")
        image = image.convert("RGBA")
        
        # Resize logo
        basewidth = 100
        wpercent = (basewidth / float(logo.size[0]))
        hsize = int((float(wpercent) * logo.size[1]))
        logo = logo.resize((basewidth, hsize), Image.LANCZOS)
        
        # Position logo
        position = (image.width - logo.width - 10, image.height - logo.height - 10)
        
        # Composite image
        transparent = Image.new('RGBA', (image.width, image.height), (0, 0, 0, 0))
        transparent.paste(image, (0, 0))
        transparent.paste(logo, position, mask=logo)
        
        return transparent.convert("RGB")
    except Exception as e:
        print(f"Error adding watermark: {e}")
        return image

# Function to add text and watermark
def add_text_and_watermark(image, name, age, medical_record, sex, label):
    draw = ImageDraw.Draw(image)
    
    # Load a larger font (adjust the size as needed)
    font_size = 24  # Example font size
    try:
        font = ImageFont.truetype("font.ttf", size=font_size)
    except IOError:
        font = ImageFont.load_default()
        print("Error: cannot open resource, using default font.")
    
    text = f"Name: {name}, Age: {age}, Medical Record: {medical_record}, Sex: {sex}, Result: {label}"
    
    # Calculate text bounding box
    text_bbox = draw.textbbox((0, 0), text, font=font)
    text_width, text_height = text_bbox[2] - text_bbox[0], text_bbox[3] - text_bbox[1]
    text_x = 20
    text_y = 40
    padding = 10

    # Draw a filled rectangle for the background
    draw.rectangle(
        [text_x - padding, text_y - padding, text_x + text_width + padding, text_y + text_height + padding],
        fill="black"
    )
    
    # Draw text on top of the rectangle
    draw.text((text_x, text_y), text, fill=(255, 255, 255, 255), font=font)

    # Add watermark to the image
    image_with_watermark = add_watermark(image)
    
    return image_with_watermark

# Function to save patient info in HTML and accumulate data
def save_patient_info_to_html(name, age, medical_record, sex, result):
    html_content = f"""
    <html>
        <body>
            <h1>Patient Information</h1>
            <p><strong>Name:</strong> {name}</p>
            <p><strong>Age:</strong> {age}</p>
            <p><strong>Medical Record:</strong> {medical_record}</p>
            <p><strong>Sex:</strong> {sex}</p>
            <p><strong>Result:</strong> {result}</p>
            <hr>
        </body>
    </html>
    """
    
    # Check if the HTML file already exists
    if html_file_path.exists():
        with open(html_file_path, 'a') as f:
            f.write(html_content)
    else:
        with open(html_file_path, 'w') as f:
            f.write(html_content)
    
    return str(html_file_path)

# Function to download the folders
def download_folder(folder):
    zip_path = os.path.join(tempfile.gettempdir(), f"{folder}.zip")
    
    # Zip the folder
    shutil.make_archive(zip_path.replace('.zip', ''), 'zip', folder)
    
    return zip_path

# Gradio Interface
def interface(name, age, medical_record, sex, input_image):
    if input_image is None:
        return None, "Please upload an image.", None

    output_image, raw_result = predict_image(input_image, name, age, medical_record, sex)
    
    if output_image is None:
        return None, raw_result, None
    
    # Save patient info to HTML
    html_file_path = save_patient_info_to_html(name, age, medical_record, sex, raw_result)
    
    # Encode the image to display in Gradio
    buffered = BytesIO()
    output_image.save(buffered, format="PNG")
    img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
    
    # Provide the zip file path for download
    zip_file = download_folder(predicted_folder)
    
    return f'<img src="data:image/png;base64,{img_str}" alt="Processed Image"/>', raw_result, zip_file

# Define Gradio interface
gr.Interface(
    fn=interface,
    inputs=[
        gr.Textbox(label="Name"),
        gr.Textbox(label="Age"),
        gr.Textbox(label="Medical Record"),
        gr.Dropdown(label="Sex", choices=["Male", "Female", "Other"]),
        gr.Image(source="upload", tool="editor", label="Upload an Image")
    ],
    outputs=[
        gr.HTML(label="Processed Image"),
        gr.Textbox(label="Raw Predictions"),
        gr.File(label="Download ZIP")
    ],
    title="Patient Image Analysis"
).launch()