Read the statement by Michael Teeuw here.
Facial Recognition - customize your mirror for every user!
-
Someone know if this module could work with a USB webcam? I try but don´t recognize me. I have the training.xml document on the folder, then start the MagicMirror and Raspberry start the module, but then nothing. I need to do something else? Need to configure in a different way? Or not be possible?
Log:
> magicmirror@2.0.0 start /home/pi/MagicMirror > electron js/electron.js Loading config ... Loading module helpers ... No helper found for module: alert. No helper found for module: clock. Initializing new module helper ... No helper found for module: compliments. No helper found for module: currentweather. No helper found for module: weatherforecast. Initializing new module helper ... Initializing new module helper ... All module helpers loaded. Starting server op port 8080 ... Server started ... Connecting socket for: calendar Starting node helper for: calendar Connecting socket for: newsfeed Starting module: newsfeed Connecting socket for: MMM-Facial-Recognition Staring module helper: MMM-Facial-Recognition Sockets connected & modules started ... Launching application. Create new calendar fetcher for url: https://calendar.google.com/calendar/ical/es.ar%23holiday%40group.v.calendar.google.com/public/basic.ics - Interval: 300000 Create new news fetcher for url: http://www.ole.com.ar/rss/ultimas-noticias/ - Interval: 300000 Can't parse feed item: Title: undefined Description: Pubdate: undefined [MMM-Facial-Recognition] Facerecognition started... [MMM-Facial-Recognition] Loading training data... [MMM-Facial-Recognition] ALGORITHM: LBPH [MMM-Facial-Recognition] Training data loaded! [MMM-Facial-Recognition] -------------------- [MMM-Facial-Recognition] Webcam ausgewählt...
Note from admin: Please use Markdown on code snippets!
-
@piedaniel did you set “useUSBCam” to True in the config.js?
-
yes, I configure in true useUSBCam.
-
I’m holding off on the facial recognition until I can figure out how to use in conjunction with pir sensor to turn mirror on and off…
-
Can anyone show me an example of how the classes should sit in the config.js file? I’m confused
-
Take a look at the stock
~/MagicMiror/config/config.js.samplefile. That should give you a good start. -
im stuck at this part of the facial recognition tools - “Write down the [‘name’, ‘name2’,‘name3’] part because you will later need it for setting up your mirror’s face recognition.” , Where do i find those names ? i see a folder has been created in the training data , but training.xml doesnt have any names
-
Nevermind , got it , stupid mistake
-
Hello,
I just discovered this project and i want to try this module before to build my MagicMirror !!!i’ve got a problem with the facial recognition tools…
i use a usbcam, i try with fswebcam without problem, i enable the webcam in raspi-config but when i trycapture.py, i’ve got a errorCapturing positive training images. Type c (and press enter) to capture an image. Press Ctrl-C to quit. c Capturing image... mmal: mmal_vc_component_create: failed to create component 'vc.ril.camera' (1:ENOMEM) mmal: mmal_component_create_core: could not create component 'vc.ril.camera' (1) Traceback (most recent call last): File "capture.py", line 35, in <module> capture.capture() File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-Tools/facetrainer/lib/capture.py", line 55, in capture image = camera.read() File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-Tools/facetrainer/lib/picam.py", line 23, in read with picamera.PiCamera() as camera: File "/usr/lib/python2.7/dist-packages/picamera/camera.py", line 488, in __init__ self.STEREO_MODES[stereo_mode], stereo_decimate) File "/usr/lib/python2.7/dist-packages/picamera/camera.py", line 526, in _init_camera "Camera is not enabled. Try running 'sudo raspi-config' " picamera.exc.PiCameraError: Camera is not enabled. Try running 'sudo raspi-config' and ensure that the camera has been enabled.Can you help me ?
ThankNote from admin: Please use Markdown on shell snippets!
-
@lepetitnicolas To my knowledge , capture .py only works with the built in webcam , that is , the pi camera module . Plus , if you are already taking images via fswebcam , why not just select option 2 in capture.py, the one with using already existing .jpg files ? Why capture again ?
