Facial recognition: no users

mc_landin

Hi,
I am an absolute nooby when it comes to Raspberry’s and programming. I’m trying to get the facial recognition to work. However, I can’t get step 5 from the training model: “Copy down the [‘name’, ‘name2’,‘name3’] part because you will later need it for setting up your mirror’s face recognition and to test your face recognition model.” to work.

A training file is generated, but there is no names part in the document? When I use the test tool the faces are recognised, however.

mc_landin

No-one able to help me out? :)

j.e.f.f

@mc_landin you need to specify the list of users in the same order as the training model outputs in your config for MMM-FacialRecognition.

example:

    {
      module: "MMM-Facial-Recognition",
      config: {
        recognitionAlgorithm: 1,
        lbphThreshold: 50,
        fisherThreshold: 250,
        eigenThreshold: 3000,
        useUSBCam: false,
        trainingFile: "modules/MMM-Facial-Recognition-Tools/training.xml",
        interval: 1,
        logoutDelay: 15,
        users: [‘name’,‘name2’,‘name3’],  /* put the list of users here. Order MUST be the same */
        defaultClass: "default",
        everyoneClass: "everyone",
        welcomeMessage: false,
        useProfileSwitcher: true
      }
    }, 
``

mc_landin

@j.e.f.f said in Facial recognition: no users:

your

Hi @j-e-f-f, thanks for the comment. my training model output does not seem to indicate any users?

j.e.f.f

@mc_landin ah sorry I don’t know why that is then.

mc_landin

Anyone, please?

mc_landin

I am now a little further. It recognises me when I use the test tool, and when I am actually running the mirror, modules containing the class of my name are hidden. However, they do not actually become visible even when I am in front of the mirror?

mc_landin

Here is my code:

{
  module: "MMM-Facial-Recognition",
  config: {
   recognitionAlgorithm:1,
   lbphTreshold: 80,
   useUSBCam: false,
   trainingfile: 'modules/MMM-Facial-Recognition/Training.xml',
   interval: 2,
   logoutDelay: 15,
   users: ['Sander'],
   defaultclass: "default",
   everyoneClass: "everyone",
   welcomeMessage: true
  }
}

PM2 logs mm specifies there is an issue, but doesn’t state what

mc_landin

Forgot to add the errors:

0|mm       |     model.load(config.get("trainingFile"))
0|mm       | cv2.error: /build/opencv-ISmtkH/opencv-2.4.9.1+dfsg/modules/contrib/src/facerec.cpp:325: error: (-2) File can't be opened for writing! in function load
0|mm       | 
0|mm       | 
0|mm       |     at PythonShell.parseError (/home/pi/MagicMirror/modules/node_modules/python-shell/index.js:190:17)
0|mm       |     at terminateIfNeeded (/home/pi/MagicMirror/modules/node_modules/python-shell/index.js:98:28)
0|mm       |     at ChildProcess. (/home/pi/MagicMirror/modules/node_modules/python-shell/index.js:88:9)
0|mm       |     at emitTwo (events.js:106:13)
0|mm       |     at ChildProcess.emit (events.js:191:7)
0|mm       |     at Process.ChildProcess._handle.onexit (internal/child_process.js:215:12)
0|mm       |   executable: 'python',
0|mm       |   options: null,
0|mm       |   script: 'modules/MMM-Facial-Recognition/facerecognition/facerecognition.py',
0|mm       |   args: [ '{"recognitionAlgorithm":1,"lbphThreshold":80,"fisherThreshold":250,"eigenThreshold":3000,"useUSBCam":false,"trainingFile":"modules/MMM-Facial-Recognition/Training.xml","interval":2,"logoutDelay":15,"users":["Sander"],"defaultClass":"default","everyoneClass":"everyone","welcomeMessage":true}' ],
0|mm       |   exitCode: 1 }