Update app.py

app.py

@@ -47,11 +47,15 @@ def fetch_recent_activity():
 # Load pre-trained emotion detection model
 @st.cache_resource
 def load_emotion_model():
-    model = load_model('CNN_Model_acc_75.h5')
-    return model
+    try:
+        model = load_model('CNN_Model_acc_75.h5')
+        return model
+    except Exception as e:
+        st.error("Error loading the emotion detection model. Please ensure the file exists and is accessible.")
+        return None
 
 emotion_model = load_emotion_model()
-emotion_labels = ['angry', 'fear', 'happy', 'neutral', 'sad', 'surprise']
+emotion_labels = ['angry', 'fear', 'happy', 'neutral', 'sad', 'surprise'] if emotion_model else []
 
 # Initialize LBPH face recognizer
 face_recognizer = cv2.face.LBPHFaceRecognizer_create()
@@ -63,12 +67,14 @@ def train_recognizer():
         for filename in os.listdir(os.path.join(KNOWN_FACES_DIR, name)):
             filepath = os.path.join(KNOWN_FACES_DIR, name, filename)
             image = cv2.imread(filepath, cv2.IMREAD_GRAYSCALE)
-            faces.append(image)
-            labels.append(name)
+            if image is not None:
+                faces.append(image)
+                labels.append(name)
     label_ids = {name: idx for idx, name in enumerate(set(labels))}
     label_ids_rev = {idx: name for name, idx in label_ids.items()}
     labels = [label_ids[label] for label in labels]
-    face_recognizer.train(faces, np.array(labels))
+    if faces:
+        face_recognizer.train(faces, np.array(labels))
     return label_ids_rev
 
 label_ids_rev = train_recognizer()
@@ -80,38 +86,46 @@ sidebar_choice = st.sidebar.selectbox("Choose an option", ["Emotion Detection",
 if sidebar_choice == "Register New Face":
     st.header("Register New Face")
     name = st.text_input("Enter Name")
-    capture_button = st.button("Capture Face via Camera")
+    capture_button = st.button("Capture Face")
+
     if capture_button and name:
         cap = cv2.VideoCapture(0)
         st.write("Capturing face... Look into the camera.")
         captured_faces = []
         face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
 
-        while len(captured_faces) < 5:
+        while len(captured_faces) < 5:  # Capture 5 images
             ret, frame = cap.read()
             if not ret:
                 st.error("Error capturing video")
                 break
+
             gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
             faces = face_cascade.detectMultiScale(gray_frame, scaleFactor=1.1, minNeighbors=5, minSize=(100, 100))
+
             for (x, y, w, h) in faces:
                 face_roi = gray_frame[y:y + h, x:x + w]
                 captured_faces.append(face_roi)
                 cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
+
             cv2.imshow("Face Registration", frame)
             if cv2.waitKey(1) & 0xFF == ord('q'):
                 break
+
         cap.release()
         cv2.destroyAllWindows()
 
-        # Save faces
-        person_dir = os.path.join(KNOWN_FACES_DIR, name)
-        if not os.path.exists(person_dir):
-            os.makedirs(person_dir)
-        for i, face in enumerate(captured_faces):
-            cv2.imwrite(os.path.join(person_dir, f"{name}_{i}.jpg"), face)
-        label_ids_rev = train_recognizer()
-        st.success(f"{name} has been registered successfully!")
+        if captured_faces:
+            person_dir = os.path.join(KNOWN_FACES_DIR, name)
+            if not os.path.exists(person_dir):
+                os.makedirs(person_dir)
+            for i, face in enumerate(captured_faces):
+                cv2.imwrite(os.path.join(person_dir, f"{name}_{i}.jpg"), face)
+
+            label_ids_rev = train_recognizer()
+            st.success(f"{name} has been registered successfully with {len(captured_faces)} captured images!")
+        else:
+            st.warning("No faces captured. Please try again.")
 
 elif sidebar_choice == "View Recent Activity":
     st.header("Recent Activity")
@@ -137,51 +151,24 @@ else:  # Emotion Detection
             label_id, confidence = face_recognizer.predict(face_resized)
             label = label_ids_rev.get(label_id, "Unknown")
 
-            # Emotion Detection
-            face_color = cv2.resize(frame[y:y + h, x:x + w], (48, 48)) / 255.0
-            face_color = np.expand_dims(cv2.cvtColor(face_color, cv2.COLOR_BGR2RGB), axis=0)
-            emotion_prediction = emotion_model.predict(face_color)
-            emotion = emotion_labels[np.argmax(emotion_prediction[0])]
-
-            # Log Attendance
-            log_attendance(label, emotion)
+            if emotion_model:
+                face_color = cv2.resize(frame[y:y + h, x:x + w], (48, 48)) / 255.0
+                face_color = np.expand_dims(cv2.cvtColor(face_color, cv2.COLOR_BGR2RGB), axis=0)
+                emotion_prediction = emotion_model.predict(face_color)
+                emotion = emotion_labels[np.argmax(emotion_prediction[0])]
 
-            # Annotate frame
-            result_text = f"{label} is feeling {emotion}"
-            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
-            cv2.putText(frame, result_text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+                log_attendance(label, emotion)
+                result_text = f"{label} is feeling {emotion}"
+                cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
+                cv2.putText(frame, result_text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
         return frame, result_text
 
- if mode == "Image":
-    uploaded_image = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"])
-    name_for_image = st.text_input("Enter Name (optional, for registration):")
-    register_image_button = st.button("Register Image")
-
-    if uploaded_image:
-        image = np.array(Image.open(uploaded_image))
-        gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-        faces = face_cascade.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(100, 100))
-
-        if len(faces) > 0:
-            for (x, y, w, h) in faces:
-                face_roi = gray_image[y:y + h, x:x + w]
-                cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)  # Annotate detected face
-
-                # Save face if user provides a name
-                if register_image_button and name_for_image:
-                    person_dir = os.path.join(KNOWN_FACES_DIR, name_for_image)
-                    if not os.path.exists(person_dir):
-                        os.makedirs(person_dir)
-                    face_filename = os.path.join(person_dir, f"{name_for_image}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.jpg")
-                    cv2.imwrite(face_filename, face_roi)
-                    st.success(f"Face for {name_for_image} has been saved successfully!")
-                    label_ids_rev = train_recognizer()  # Retrain recognizer after adding new face
-
-        else:
-            st.warning("No face detected in the uploaded image. Please try another image.")
-
-        st.image(image, caption="Processed Image with Face Annotations")
-
+    if mode == "Image":
+        uploaded_image = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"])
+        if uploaded_image:
+            image = np.array(Image.open(uploaded_image))
+            frame, _ = process_frame(image)
+            st.image(frame, caption="Processed Image with Face Annotations")
 
     elif mode == "Camera":
         cap = cv2.VideoCapture(0)