app.py

import gradio as gr
from tensorflow.keras.models import model_from_json
import numpy as np
import cv2

# Load the face detection model
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

# Load the anti-spoofing model structure and weights
with open('antispoofing_model.json', 'r') as json_file:
    loaded_model_json = json_file.read()
model = model_from_json(loaded_model_json)
model.load_weights('antispoofing_model.h5')

# Define the prediction function
def predict(image):
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        face = image[y:y+h, x:x+w]
        face = cv2.resize(face, (160, 160))
        face = face.astype('float') / 255.0
        face = np.expand_dims(face, axis=0)
        pred = model.predict(face)
        label = 'Spoof' if pred > 0.5 else 'Real'
        cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)
        cv2.putText(image, label, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
    return image

# Create the Gradio interface
iface = gr.Interface(fn=predict, inputs="image", outputs="image")

# Run the interface
iface.launch()