Update app.py

app.py

@@ -2,8 +2,9 @@ import numpy as np
 import cv2
 import face_recognition
 import sqlite3
-import gradio as gr
+import streamlit as st
 from datetime import datetime
+from PIL import Image
 
 # Step 1: Initialize Face Recognition
 # Load known faces and names
@@ -11,10 +12,13 @@ known_face_encodings = []
 known_face_names = []
 
 # Example: Add known faces
-image_person1 = face_recognition.load_image_file("person1.jpg")
-encoding_person1 = face_recognition.face_encodings(image_person1)[0]
-known_face_encodings.append(encoding_person1)
-known_face_names.append("Person 1")
+try:
+    image_person1 = face_recognition.load_image_file("person1.jpg")
+    encoding_person1 = face_recognition.face_encodings(image_person1)[0]
+    known_face_encodings.append(encoding_person1)
+    known_face_names.append("Person 1")
+except Exception as e:
+    st.error(f"Error loading known faces: {e}")
 
 # Step 2: Set Up Database
 connection = sqlite3.connect("attendance.db", check_same_thread=False)
@@ -34,9 +38,9 @@ def log_attendance(name):
     connection.commit()
 
 # Step 3: Detect and Recognize Faces
-def detect_and_mark_attendance(image):
-    image_np = np.array(image)
-    rgb_image = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
+def detect_and_mark_attendance(uploaded_image):
+    image = np.array(uploaded_image)
+    rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
     face_locations = face_recognition.face_locations(rgb_image)
     face_encodings = face_recognition.face_encodings(rgb_image, face_locations)
     
@@ -50,10 +54,10 @@ def detect_and_mark_attendance(image):
             log_attendance(name)  # Log to database
 
         # Draw a rectangle around the face
-        cv2.rectangle(image_np, (left, top), (right, bottom), (255, 0, 0), 3)
-        cv2.putText(image_np, name, (left, top - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+        cv2.rectangle(image, (left, top), (right, bottom), (255, 0, 0), 3)
+        cv2.putText(image, name, (left, top - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
 
-    return image_np
+    return image
 
 # Step 4: Fetch Attendance Logs
 def fetch_attendance():
@@ -61,21 +65,26 @@ def fetch_attendance():
     rows = cursor.fetchall()
     return rows
 
-# Step 5: Gradio Interface
-iface = gr.Interface(
-    fn=detect_and_mark_attendance,
-    inputs="image",
-    outputs="image",
-    title="Face Recognition and Attendance",
-    description="Upload an image to detect and mark attendance. Attendance will be saved to the database."
-)
+# Streamlit Interface
+st.title("Face Recognition and Attendance System")
+st.write("Upload an image to detect faces and mark attendance.")
 
-iface.add_component(
-    fn=fetch_attendance,
-    inputs=None,
-    outputs="dataframe",
-    label="Attendance Logs"
-)
+# Image upload
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
 
-iface.launch()
+if uploaded_image is not None:
+    image = Image.open(uploaded_image)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    # Process image
+    image_np = np.array(image)
+    processed_image = detect_and_mark_attendance(image_np)
+    st.image(processed_image, caption="Processed Image with Attendance Marked", use_column_width=True)
 
+# Display attendance logs
+st.subheader("Attendance Logs")
+attendance_data = fetch_attendance()
+if attendance_data:
+    st.table(attendance_data)
+else:
+    st.write("No attendance records found.")