app.py

import gradio as gr
import tensorflow as tf
import cv2
import numpy as np
import os
import time
import dlib
import mediapipe as mp
from skimage import feature
# from your_cnn_model import YourCNNModel  # Import your CNN model

class AntiSpoofingSystem:
    def __init__(self):
        self.detector = dlib.get_frontal_face_detector()
        self.predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
        self.mp_hands = mp.solutions.hands
        self.hands = self.mp_hands.Hands(static_image_mode=False, max_num_hands=1, min_detection_confidence=0.7)
        self.net_smartphone = cv2.dnn.readNet('yolov4.weights', 'yolov4.cfg')
        with open('coco.names', 'r') as f:
            self.classes_smartphone = f.read().strip().split('\n')
        self.EAR_THRESHOLD = 0.25
        self.BLINK_CONSEC_FRAMES = 4
        self.left_eye_state = False
        self.right_eye_state = False
        self.left_blink_counter = 0
        self.right_blink_counter = 0
        self.smartphone_detected = False
        self.smartphone_detection_frame_interval = 30
        self.frame_count = 0

    def calculate_ear(self, eye):
        A = np.linalg.norm(eye[1] - eye[5])
        B = np.linalg.norm(eye[2] - eye[4])
        C = np.linalg.norm(eye[0] - eye[3])
        return (A + B) / (2.0 * C)

    def analyze_texture(self, face_region):
        gray_face = cv2.cvtColor(face_region, cv2.COLOR_BGR2GRAY)
        lbp = feature.local_binary_pattern(gray_face, P=8, R=1, method="uniform")
        lbp_hist, _ = np.histogram(lbp.ravel(), bins=np.arange(0, 58), range=(0, 58))
        lbp_hist = lbp_hist.astype("float")
        lbp_hist /= (lbp_hist.sum() + 1e-5)
        return np.sum(lbp_hist[:10]) > 0.3

    def detect_hand_gesture(self, frame):
        results = self.hands.process(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
        return results.multi_hand_landmarks is not None

    def detect_smartphone(self, frame):
        if self.frame_count % self.smartphone_detection_frame_interval == 0:
            blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416), swapRB=True, crop=False)
            self.net_smartphone.setInput(blob)
            output_layers_names = self.net_smartphone.getUnconnectedOutLayersNames()
            detections = self.net_smartphone.forward(output_layers_names)
            for detection in detections:
                for obj in detection:
                    scores = obj[5:]
                    class_id = np.argmax(scores)
                    confidence = scores[class_id]
                    if confidence > 0.5 and self.classes_smartphone[class_id] == 'cell phone':
                        self.smartphone_detected = True
                        self.left_blink_counter = 0
                        self.right_blink_counter = 0
                        return
        self.frame_count += 1
        self.smartphone_detected = False

    def detect_blink(self, left_ear, right_ear):
        if self.smartphone_detected:
            self.left_eye_state = False
            self.right_eye_state = False
            self.left_blink_counter = 0
            self.right_blink_counter = 0
            return False

        if left_ear < self.EAR_THRESHOLD:
            if not self.left_eye_state:
                self.left_eye_state = True
        else:
            if self.left_eye_state:
                self.left_eye_state = False
                self.left_blink_counter += 1

        if right_ear < self.EAR_THRESHOLD:
            if not self.right_eye_state:
                self.right_eye_state = True
        else:
            if self.right_eye_state:
                self.right_eye_state = False
                self.right_blink_counter += 1

        return self.left_blink_counter > 0 and self.right_blink_counter > 0

    def run(self, input_image):
        frame = input_image
        blink_count = 0
        hand_gesture_detected = False
        real_person_detected = False
        cropped_face = None

        self.detect_smartphone(frame)

        if not self.smartphone_detected:
            gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
            faces = self.detector(gray)

            for face in faces:
                landmarks = self.predictor(gray, face)
                leftEye = np.array([(landmarks.part(n).x, landmarks.part(n).y) for n in range(36, 42)])
                rightEye = np.array([(landmarks.part(n).x, landmarks.part(n).y) for n in range(42, 48)])

                ear_left = self.calculate_ear(leftEye)
                ear_right = self.calculate_ear(rightEye)

                if self.detect_blink(ear_left, ear_right):
                    blink_count += 1

                hand_gesture_detected = self.detect_hand_gesture(frame)

                (x, y, w, h) = (face.left(), face.top(), face.width(), face.height())
                cropped_face = frame[max(y - h // 2, 0):min(y + 3 * h // 2, frame.shape[0]),
                                     max(x - w // 2, 0):min(x + 3 * w // 2, frame.shape[1])]

                if blink_count >= 5 and hand_gesture_detected and self.analyze_texture(cropped_face):
                    real_person_detected = True
                    break

        return real_person_detected, cropped_face

# Initialize the anti-spoofing system
anti_spoofing_system = AntiSpoofingSystem()

# Load your CNN model (this is a placeholder for your actual model loading code)
supervised_embedding_model = tf.keras.models.load_model('v3_embedding_model (2).h5')
#cnn_model.load_weights('v3_embedding_model (2).h5')

def process_frame(image):
    real_person_detected, cropped_face = anti_spoofing_system.run(image)

    if not real_person_detected:
        return image, "No real person detected or spoofing attempt."

    # Placeholder for actual CNN model prediction
    person_id, confidence = "PersonID", 0.99  # Replace with your CNN model logic

    result_text = f"Person identified: {person_id} with confidence: {confidence}" if person_id else "Person not recognized. Registration required."
    cv2.putText(image, result_text, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2)
    return image

def video_stream():
    cap = cv2.VideoCapture(0)
    while True:
        ret, frame = cap.read()
        if not ret:
            break
        processed_frame = process_frame(frame)
        yield processed_frame

iface = gr.Interface(
    fn=video_stream,
    inputs=None,
    outputs=gr.outputs.Video(label="Output Video"),
    live=True,
    title="Live Face Recognition and Verification System",
    description="Live detection and verification of persons from a camera feed."
)

if __name__ == "__main__":
    iface.launch()