Update app.py

app.py

@@ -1,88 +1,106 @@
 import streamlit as st
-from streamlit_webrtc import webrtc_streamer, VideoTransformerBase, VideoFrame
+from streamlit_webrtc import webrtc_streamer, VideoTransformerBase
 import cv2
+import av
 import numpy as np
-from datetime import datetime
-from keras.models import load_model
-import sqlite3
 import os
+from datetime import datetime
+
+# Directory to store registered faces
+KNOWN_FACES_DIR = "known_faces"
+os.makedirs(KNOWN_FACES_DIR, exist_ok=True)
+
+# Page configuration
+st.set_page_config(page_title="Face Detection App", layout="wide")
+
+# Title and Description
+st.title("Face Detection and Registration App")
+st.write("""
+This app allows you to:
+1. Detect faces in real-time using your webcam.
+2. Register new faces with names.
+3. View the list of registered faces.
+4. Show recent activity logs.
+""")
 
-# Database Initialization
-DB_NAME = "emotion_detection.db"
-
-def initialize_database():
-    conn = sqlite3.connect(DB_NAME)
-    cursor = conn.cursor()
-    cursor.execute("""
-    CREATE TABLE IF NOT EXISTS face_data (
-        id INTEGER PRIMARY KEY AUTOINCREMENT,
-        name TEXT NOT NULL,
-        emotion TEXT NOT NULL,
-        timestamp TEXT NOT NULL
-    )
-    """)
-    conn.commit()
-    conn.close()
-
-initialize_database()
-
-# Load emotion detection model
-@st.cache_resource
-def load_emotion_model():
-    return load_model('CNN_Model_acc_75.h5')
-
-emotion_model = load_emotion_model()
-emotion_labels = ['angry', 'fear', 'happy', 'neutral', 'sad', 'surprise']
-
-# Video Transformer for Streamlit WebRTC
-class EmotionDetector(VideoTransformerBase):
+# Initialize log list
+activity_log = []
+
+# Define Video Processor
+class VideoProcessor(VideoTransformerBase):
     def __init__(self):
-        self.model = emotion_model
+        self.face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
+        self.registering_face = False
+        self.face_name = None
+
+    def set_registering_mode(self, name):
+        self.registering_face = True
+        self.face_name = name
 
-    def transform(self, frame: VideoFrame) -> VideoFrame:
+    def stop_registering(self):
+        self.registering_face = False
+        self.face_name = None
+
+    def recv(self, frame):
         img = frame.to_ndarray(format="bgr24")
         gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-        faces = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml").detectMultiScale(
-            gray, scaleFactor=1.1, minNeighbors=5, minSize=(48, 48)
-        )
 
+        # Detect faces
+        faces = self.face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(50, 50))
+
+        # Draw rectangles and save face images if in registering mode
         for (x, y, w, h) in faces:
-            face = gray[y:y + h, x:x + w]
-            face_resized = cv2.resize(face, (48, 48))
-            face_normalized = face_resized / 255.0
-            face_reshaped = np.reshape(face_normalized, (1, 48, 48, 1))
-            
-            prediction = self.model.predict(face_reshaped)
-            emotion = emotion_labels[np.argmax(prediction[0])]
-            
-            # Draw bounding box and label
             cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
-            cv2.putText(img, emotion, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
-
-        return VideoFrame.from_ndarray(img, format="bgr24")
-
-# Sidebar menu
-menu = st.sidebar.selectbox("Menu", ["Home", "View Records"])
-
-if menu == "Home":
-    st.title("Real-Time Emotion Detection")
-    st.write("Using your camera for real-time emotion detection.")
-    
-    webrtc_streamer(
-        key="emotion-detection",
-        video_transformer_factory=EmotionDetector,
-        media_stream_constraints={"video": True, "audio": False},
-    )
-
-elif menu == "View Records":
-    st.title("View Records")
-    st.subheader("Recent Records")
-    
-    conn = sqlite3.connect(DB_NAME)
-    cursor = conn.cursor()
-    cursor.execute("SELECT name, emotion, timestamp FROM face_data ORDER BY timestamp DESC LIMIT 5")
-    records = cursor.fetchall()
-    conn.close()
-
-    for record in records:
-        st.write(f"**Name**: {record[0]}, **Emotion**: {record[1]}, **Timestamp**: {record[2]}")
+            if self.registering_face:
+                face_img = img[y:y + h, x:x + w]
+                face_path = os.path.join(KNOWN_FACES_DIR, f"{self.face_name}_{datetime.now().strftime('%Y%m%d%H%M%S')}.jpg")
+                cv2.imwrite(face_path, face_img)
+                self.registering_face = False
+                st.session_state.activity_log.append(f"Face registered: {self.face_name} at {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+
+        return av.VideoFrame.from_ndarray(img, format="bgr24")
+
+
+# Sidebar for navigation
+st.sidebar.title("Options")
+app_mode = st.sidebar.radio("Choose the mode:", ["Real-time Face Detection", "Register a New Face", "View Registered Faces", "Recent Activity"])
+
+# Global activity log state
+if "activity_log" not in st.session_state:
+    st.session_state.activity_log = []
+
+# Handle the selected mode
+if app_mode == "Real-time Face Detection":
+    st.header("Real-time Face Detection")
+    webrtc_streamer(key="face_detection", video_processor_factory=VideoProcessor)
+
+elif app_mode == "Register a New Face":
+    st.header("Register a New Face")
+    name = st.text_input("Enter the name for the new face:")
+    if st.button("Start Registration"):
+        if not name.strip():
+            st.error("Name cannot be empty!")
+        else:
+            processor = webrtc_streamer(key="register_face", video_processor_factory=VideoProcessor)
+            if processor.video_processor:
+                processor.video_processor.set_registering_mode(name)
+                st.success(f"Registering face for '{name}'. Please look into the camera.")
+
+elif app_mode == "View Registered Faces":
+    st.header("Registered Faces")
+    faces = os.listdir(KNOWN_FACES_DIR)
+    if faces:
+        st.write(f"**Total Faces Registered:** {len(faces)}")
+        for face in faces:
+            st.write(face)
+    else:
+        st.write("No faces have been registered yet.")
+
+elif app_mode == "Recent Activity":
+    st.header("Recent Activity Log")
+    if st.session_state.activity_log:
+        for log in reversed(st.session_state.activity_log):
+            st.write(log)
+    else:
+        st.write("No activity logged yet.")
+