Update app.py

app.py

@@ -1,47 +1,99 @@
 import streamlit as st
 from PIL import Image
-import torch
-from torchvision import transforms
-from transformers import pipeline
+import face_recognition
+import cv2
+import numpy as np
+import os
+from datetime import datetime
 
-# Load the face detection model
-face_detector = pipeline('face-detection', model='facebook/facemask-plugin-fasterrcnn')
+st.title("AIMLJan24 - Face Recognition")
 
-# Function to detect faces in an image
-def detect_faces(image):
-    # Convert image to PyTorch tensor
-    image_tensor = transforms.ToTensor()(image).unsqueeze(0)
+# Load images for face recognition
+Images = []   
+classnames = []  
+directory = "photos"
+myList = os.listdir(directory)
 
-    # Detect faces
-    faces = face_detector(image_tensor)
+st.write("Photographs found in folder : ")
+for cls in myList:
+    if os.path.splitext(cls)[1] in [".jpg", ".jpeg"]:
+        img_path = os.path.join(directory, cls)
+        curImg = cv2.imread(img_path)
+        Images.append(curImg)
+        st.write(os.path.splitext(cls)[0])
+        classnames.append(os.path.splitext(cls)[0])
 
-    return faces
+# Load images for face recognition
+encodeListknown = [face_recognition.face_encodings(img)[0] for img in Images]
 
-# Streamlit app
-def main():
-    st.title("Multiple Face Detection using Hugging Face")
+# camera to take photo of user in question
+file_name = st.file_uploader("Upload image")
 
-    uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+def add_attendance(name):
+    username = name
+    current_datetime = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    print(current_datetime)
+    
+    if not os.path.isdir('Attendance'):
+        os.makedirs('Attendance')
 
-    if uploaded_file is not None:
-        # Read the image
-        image = Image.open(uploaded_file)
-        st.image(image, caption="Uploaded Image", use_column_width=True)
+    if f'Attendance-{current_datetime}.csv' not in os.listdir('Attendance'):
+        with open(f'Attendance/Attendance-{current_datetime}.csv', 'w') as f:
+            f.write('Name,Time')
+   
 
-        # Detect faces
-        faces = detect_faces(image)
+if file_name is not None:
+    col1, col2 = st.columns(2)
 
-        # Display the number of faces detected
-        num_faces = len(faces)
-        st.write(f"Number of faces detected: {num_faces}")
+    test_image = Image.open(file_name)
+    image = np.asarray(test_image)
 
-        # Display bounding boxes around detected faces
-        for face in faces:
-            xmin, ymin, xmax, ymax = face['box']
-            image_with_box = image.copy()
-            draw = ImageDraw.Draw(image_with_box)
-            draw.rectangle([xmin, ymin, xmax, ymax], outline="red", width=3)
-            st.image(image_with_box, caption="Face Detection", use_column_width=True)
+    imgS = cv2.resize(image, (0, 0), None, 0.25, 0.25)
+    imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)
+    facesCurFrame   = face_recognition.face_locations(imgS)
+    encodesCurFrame = face_recognition.face_encodings(imgS, facesCurFrame)
 
-if __name__ == "__main__":
-    main()
+    # List to store recognized names for all faces in the image
+    recognized_names = []
+
+    # Checking if faces are detected
+    if len(encodesCurFrame) > 0:
+        for encodeFace, faceLoc in zip(encodesCurFrame, facesCurFrame):
+            # Assuming that encodeListknown is defined and populated in your code
+            matches = face_recognition.compare_faces(encodeListknown, encodeFace)
+            faceDis = face_recognition.face_distance(encodeListknown, encodeFace)
+            
+            # Initialize name as Unknown
+            name = "Unknown"
+
+            # Check if there's a match with known faces
+            if True in matches:
+                matchIndex = np.argmin(faceDis)
+                name = classnames[matchIndex].upper()
+                
+            # Append recognized name to the list
+            recognized_names.append(name)
+
+            # Draw rectangle and label on the image
+            y1, x2, y2, x1 = faceLoc
+            y1, x2, y2, x1 = (y1 * 4), (x2 * 4), (y2 * 4) ,(x1 * 4)
+            
+            # Make a copy of the image array before drawing on it
+            image_copy = image.copy()
+            
+            cv2.rectangle(image_copy, (x1, y1), (x2, y2), (0, 255, 0), 2)
+            cv2.rectangle(image_copy, (x1, y2 - 35), (x2, y2), (0, 255, 0), cv2.FILLED)
+            cv2.putText(image_copy, name, (x1 + 6, y2 - 6), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 255), 2)
+
+            # Update the database
+            add_attendance(name)
+            
+        # Display the image with recognized names
+        st.image(image_copy, use_column_width=True, output_format="PNG")
+
+        # Display recognized names
+        st.write("Recognized Names:")
+        for i, name in enumerate(recognized_names):
+            st.write(f"Face {i+1}: {name}")
+    else:
+        st.warning("No faces detected in the image. Face recognition failed.")