Update app.py

app.py

@@ -4,7 +4,6 @@ import numpy as np
 import time
 import os
 from keras.models import load_model
-import face_recognition
 from PIL import Image
 import tempfile
 
@@ -37,10 +36,13 @@ def load_known_faces():
     for image_name in os.listdir(folder_path):
         if image_name.endswith(('.jpg', '.jpeg', '.png')):
             image_path = os.path.join(folder_path, image_name)
-            image = face_recognition.load_image_file(image_path)
-            encoding = face_recognition.face_encodings(image)
+            image = cv2.imread(image_path)
+            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+            faces = cv2.face.LBPHFaceRecognizer_create()
+            faces.train([gray], np.array([0]))  # This is simplified, train with multiple images
+            encoding = faces.getHistograms()
             if encoding:
-                known_faces.append(encoding[0])
+                known_faces.append(encoding)
                 known_names.append(image_name.split('.')[0])  # Assuming file name is the person's name
 load_known_faces()
 
@@ -63,13 +65,11 @@ def process_frame(frame):
         predictions = model.predict(face_roi)
         emotion = emotion_labels[np.argmax(predictions[0])]
 
-        # Face recognition
-        face_encoding = face_recognition.face_encodings(frame, [(y, x+w, y+h, x)])[0]  # Get face encoding
-        matches = face_recognition.compare_faces(known_faces, face_encoding)
+        # Face recognition using LBPH
+        label, confidence = cv2.face.LBPHFaceRecognizer_create().predict(roi_gray)
         name = "Unknown"
-        if True in matches:
-            first_match_index = matches.index(True)
-            name = known_names[first_match_index]
+        if confidence < 100:
+            name = known_names[label]
 
         # Draw bounding box and label on the frame
         cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)