Update app.py

app.py

@@ -12,29 +12,34 @@ import matplotlib.pyplot as plt
 import pylab # this allows you to control figure size 
 pylab.rcParams['figure.figsize'] = (10.0, 8.0) # this controls figure size in the notebook
 
-import io
-import streamlit as st
-bytes_data=None
+# import io
+# import streamlit as st
+# bytes_data=None
 
 ##################################################3
 
+import gradio as gr
+
+
+
+
 app = Flask(__name__)
 
-flag1 = True
+# flag1 = True
 
-@app.route('/at')
-def testme():
-    global flag1
-    # return "i am in testme"
-    while flag1 is True:
+# @app.route('/at')
+# def testme():
+#     global flag1
+#     # return "i am in testme"
+#     while flag1 is True:
         
-        img_file_buffer=st.camera_input("Take a picture")
-        if img_file_buffer is not None:
-            test_image = Image.open(img_file_buffer)
-            st.image(test_image, use_column_width=True)
-        if bytes_data is None:
-            flag1 = False
-            st.stop()
+#         img_file_buffer=st.camera_input("Take a picture")
+#         if img_file_buffer is not None:
+#             test_image = Image.open(img_file_buffer)
+#             st.image(test_image, use_column_width=True)
+#         if bytes_data is None:
+#             flag1 = False
+#             st.stop()
 
 # def attend():
 #     # Face recognition variables
@@ -123,11 +128,116 @@ def testme():
 #     run_face_recognition()
 
 #     return redirect(url_for('show_table'))
+##########################################################################
+def snap(image,video):
+    return [image,video]
 
 
+@app.route('/at')
+def attend():
+    # Face recognition variables
+    known_faces_names = ["Sarwan Sir", "Vikas","Lalit","Jasmeen","Anita Ma'am"]
+    known_face_encodings = []
 
-   
+    # Load known face encodings
+    sir_image = face_recognition.load_image_file("photos/sir.jpeg")
+    sir_encoding = face_recognition.face_encodings(sir_image)[0]
+
+    vikas_image = face_recognition.load_image_file("photos/vikas.jpg")
+    vikas_encoding = face_recognition.face_encodings(vikas_image)[0]
+
+    lalit_image = face_recognition.load_image_file("photos/lalit.jpg")
+    lalit_encoding = face_recognition.face_encodings(lalit_image)[0]
+
+    jasmine_image = face_recognition.load_image_file("photos/jasmine.jpg")
+    jasmine_encoding = face_recognition.face_encodings(jasmine_image)[0]
+
+    maam_image = face_recognition.load_image_file("photos/maam.png")
+    maam_encoding = face_recognition.face_encodings(maam_image)[0]
+
+    known_face_encodings = [sir_encoding, vikas_encoding,lalit_encoding,jasmine_encoding,maam_encoding]
+
+    students = known_faces_names.copy()
+
+    face_locations = []
+    face_encodings = []
+    face_names = []
+
+    now = datetime.now()
+    current_date = now.strftime("%Y-%m-%d")
+    csv_file = open(f"{current_date}.csv", "a+", newline="")
+    
+    csv_writer = csv.writer(csv_file)
+    
 
+    # Function to run face recognition
+    def run_face_recognition():
+        video_capture = cv2.VideoCapture(0)
+        s = True
+
+        existing_names = set(row[0] for row in csv.reader(csv_file))  # Collect existing names from the CSV file   
+        
+
+        while s:
+            _, frame = video_capture.read()
+            small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
+            rgb_small_frame = small_frame[:, :, ::-1]
+            
+            face_locations = face_recognition.face_locations(rgb_small_frame)
+            face_encodings = face_recognition.face_encodings(small_frame, face_locations)
+            face_names = []
+
+            for face_encoding in face_encodings:
+                matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
+                name = ""
+                face_distance = face_recognition.face_distance(known_face_encodings, face_encoding)
+                best_match_index = np.argmin(face_distance)
+                if matches[best_match_index]:
+                    name = known_faces_names[best_match_index]
+
+                face_names.append(name)
+
+               
+                for name in face_names:
+                    if name in known_faces_names and name in students and name not in existing_names:
+                        students.remove(name)
+                        print(students)
+                        print(f"Attendance recorded for {name}")
+                        current_time = now.strftime("%H-%M-%S")
+                        csv_writer.writerow([name, current_time, "Present"])
+                        existing_names.add(name)  # Add the name to the set of existing names
+                        
+                        s = False  # Set s to False to exit the loop after recording attendance
+                        break  # Break the loop once attendance has been recorded for a name
+
+            cv2.imshow("Attendance System", frame)
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                break
+
+        video_capture.release()
+        cv2.destroyAllWindows()
+        csv_file.close()
+
+    # Call the function to run face recognition
+    run_face_recognition()
+
+    return redirect(url_for('show_table'))
+
+def gradio_interface():
+    demo = gr.Interface(
+        snap,
+        [gr.Image(source="webcam", tool=None), gr.Video(source="webcam")],
+        ["image", "video"],
+    )
+    return demo
+
+
+@app.route('/gradio')
+def gradio():
+    interface = gradio_interface()
+    return interface.launch()
+    
+###########################################################################
 @app.route('/table')
 def show_table():
     # Get the current date