diff --git a/Jarvis.py b/Jarvis.py
index c20efd09..836abb7a 100644
--- a/Jarvis.py
+++ b/Jarvis.py
@@ -1,9 +1,11 @@
 from database.mongodb import create_connection, login_user
 from database.localStorageServer import server
 from src.utils.functions import application
+from src.emotion_recognition import run_emotion_detection  # Import emotion detection logic
 from datetime import datetime, timedelta
 import streamlit as st
 
+# Initialize session state if not present
 if "user" not in st.session_state:
     st.session_state.update({
         'password': None,
@@ -12,6 +14,7 @@
         'verified': False,
     })
 
+# Function to fetch credentials from local storage
 def get_credentials():
     conn = server()
     return (
@@ -21,16 +24,26 @@ def get_credentials():
         conn.getLocalStorageVal("verified"),
     )
 
+# Main execution block
 if __name__ == "__main__":
     today = datetime.now()
 
+    # Fetch credentials from local storage if password is None
     if st.session_state['password'] is None:
         st.session_state['password'], st.session_state['user'], st.session_state['expiration_date'], st.session_state['verified'] = get_credentials()
 
+    # Check if the user's session is valid and not expired
     if st.session_state['expiration_date'] > today.isoformat() and not st.session_state['verified']:
         conn = create_connection()
         if login_user(conn, st.session_state['user'][0], st.session_state['password']):
             st.session_state['verified'] = True
             server().setLocalStorageVal("verified", True)
 
+    # Run the application if the user is verified
+    if st.session_state['verified']:
+        # Optionally, run emotion detection here after user is verified
+        run_emotion_detection()  # Trigger the emotion recognition (this could be interactive in the UI)
+
+    # Run the application logic based on verified user status
     application(st.session_state['verified']).run()
+
diff --git a/emotion_model.h5 b/emotion_model.h5
new file mode 100644
index 00000000..530224fe
--- /dev/null
+++ b/emotion_model.h5
@@ -0,0 +1 @@
+model.save('assets/emotion_model.h5')  # Save the trained model to 'assets' folder
diff --git a/emotion_recognition.py b/emotion_recognition.py
new file mode 100644
index 00000000..6eb47b2a
--- /dev/null
+++ b/emotion_recognition.py
@@ -0,0 +1,60 @@
+import numpy as np
+import cv2
+from keras.models import load_model
+from keras.utils import np_utils
+
+# Emotion dictionary
+emotion_dict = {0: "Angry", 1: "Disgust", 2: "Fear", 3: "Happy", 4: "Sad", 5: "Surprise", 6: "Neutral"}
+
+def preprocess_image(image):
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # Convert to grayscale
+    image = cv2.resize(image, (48, 48))  # Resize to match model input size
+    image = image.astype('float32') / 255.0  # Normalize pixel values
+    image = np.reshape(image, (1, 48, 48, 1))  # Add a channel dimension
+    return image
+
+def load_emotion_model():
+    # Load the pre-trained model
+    model = load_model('assets/emotion_model.h5')
+    return model
+
+def detect_emotion(frame, model):
+    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+    face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+    
+    # Detect faces
+    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
+    
+    for (x, y, w, h) in faces:
+        face = gray[y:y+h, x:x+w]
+        face = preprocess_image(face)  # Preprocess the face for emotion prediction
+        emotion_pred = model.predict(face)  # Get prediction
+        max_index = np.argmax(emotion_pred[0])  # Get the emotion with highest probability
+        emotion = emotion_dict[max_index]  # Get emotion name
+        color = (0, 255, 0)  # Color for bounding box (green)
+        
+        # Draw the rectangle and emotion label on the frame
+        cv2.rectangle(frame, (x, y), (x+w, y+h), color, 2)
+        cv2.putText(frame, emotion, (x, y-10), cv2.FONT_HERSHEY_SIMPLEX, 1, color, 2)
+    
+    return frame
+
+def run_emotion_detection():
+    model = load_emotion_model()
+    cap = cv2.VideoCapture(0)  # Start webcam
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+        frame = detect_emotion(frame, model)
+        cv2.imshow('Emotion Recognition', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):  # Exit if 'q' is pressed
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+if __name__ == '__main__':
+    run_emotion_detection()  # Run the emotion detection function when this script is executed
diff --git a/requirements.txt b/requirements.txt
index ef5b47b9..c97351ff 100644
Binary files a/requirements.txt and b/requirements.txt differ
diff --git a/streamlit_app.py b/streamlit_app.py
new file mode 100644
index 00000000..938466c6
--- /dev/null
+++ b/streamlit_app.py
@@ -0,0 +1,8 @@
+import streamlit as st
+from src.emotion_recognition import run_emotion_detection
+
+st.title("Emotion Recognition with Jarvis")
+st.write("Click the button to start emotion detection.")
+
+if st.button('Start Emotion Recognition'):
+    run_emotion_detection()