Complete steps to implement face recognition login in Ubuntu

sudo add-apt-repository ppa:boltgolt/howdy
sudo apt update
sudo apt install howdy

sudo howdy add

Enter a label for this new model [Initial model] (max 24 characters): tiger
Camera path is not configured correctly, please edit the 'device_path' config value.
Exception ignored in: <bound method VideoCapture.__del__ of <recorders.video_capture.VideoCapture object at 0x7f6bc5be02b0>>
Traceback (most recent call last):
 File "/lib/security/howdy/recorders/video_capture.py", line 55, in __del__
  self.internal.release()
AttributeError: 'VideoCapture' object has no attribute 'internal'

$ sudo apt-get install v4l-utils
# View the camera path $ v4l2-ctl --list-devices
USB 2.0 Camera: USB Camera (usb-0000:03:00.0-14):
 /dev/video0
$ sudo howdy config
# Next, change the device_path in config = /dev/video0

$ sudo howdy add
Adding face model for the user tiger
Enter a label for this new model [Initial model] (max 24 characters): tiger

Please look straight into the camera
Scan complete

Added a new model to tiger

$ sudo -i
Identified face as tiger

$ sudo howdy test

Opening a window with a test feed

Press ctrl+C in this terminal to quit
Click on the image to enable or disable slow mode


Closing window

howdy [-U user] [-y] command [argument]