Great!
✅ **Multiple User Face Recognition** allows your face lock to recognize
several authorized users. This is useful for shared devices or access control
systems.
---
### 🔧 How It Works
1. Load and encode multiple authorized faces.
2. Compare webcam faces against the list of authorized encodings.
3. If a match is found, show which person was recognized and grant access.
---
### 📁 Folder Structure Example
```
face_lock_project/
├── known_faces/
│ ├── user1.jpg
│ ├── user2.jpg
│ └── user3.jpg
└── face_lock.py
```
---
### 💻 Python Code for Multiple User Face Lock
```python
import face_recognition
import cv2
import os
import numpy as np
# Load all known faces
known_face_encodings = []
known_face_names = []
known_faces_dir = "known_faces"
# Loop over all files in the known_faces directory
for filename in os.listdir(known_faces_dir):
if filename.endswith(".jpg") or filename.endswith(".png"):
path = os.path.join(known_faces_dir, filename)
image = face_recognition.load_image_file(path)
encodings = face_recognition.face_encodings(image)
if encodings:
known_face_encodings.append(encodings[0])
name = os.path.splitext(filename)[0] # Remove file extension
known_face_names.append(name)
else:
print(f"❌ No face found in {filename}")
# Start webcam
cap = cv2.VideoCapture(0)
print("🔍 Scanning for known faces... (Press 'q' to exit)")
while True:
ret, frame = cap.read()
if not ret:
break
# Resize frame for speed
small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
rgb_small_frame = small_frame[:, :, ::-1] # BGR to RGB
# Find all faces and encodings
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(rgb_small_frame,
face_locations)
# Match each face found
for face_encoding, face_location in zip(face_encodings, face_locations):
matches = face_recognition.compare_faces(known_face_encodings,
face_encoding)
face_distances = face_recognition.face_distance(known_face_encodings,
face_encoding)
name = "Unknown"
if matches:
best_match_index = np.argmin(face_distances)
if matches[best_match_index]:
name = known_face_names[best_match_index]
# Draw box and label
top, right, bottom, left = [v * 4 for v in face_location] # Scale back up
cv2.rectangle(frame, (left, top), (right, bottom), (0, 255, 0) if name !=
"Unknown" else (0, 0, 255), 2)
cv2.putText(frame, name, (left, top - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9,
(255, 255, 255), 2)
cv2.imshow("Face Lock - Multiple User", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
```
---
### ✅ Setup Instructions
1. Place one clear face photo of each user in the `known_faces/` folder.
2. The filename (e.g., `sir.jpg`) will be the name shown when recognized.
3. Run the script, and it will show “Unknown” for anyone not in the list.
---
### 🚀 Possible Add-Ons
* Face **registration system** (automatically add new users via GUI).
* Lock/unlock folder, browser, or computer session based on face.
* **Voice + Face authentication** combo.
* Save logs of who accessed and when.
Want help with any of these advanced features or GUI for easier use?
