Please read the release notes carefully since this update requires adjustments to your Raspberry Pi configuration!
Facial Rec. Attendance/Roll Taker
dimpi45 last edited by
I am building a magic mirror for my high school English classroom. I started thinking about facial recognition for differentiating upcoming assignments for different class periods, but since I have 6 classes with 40 students, I decided I have neither the time or patience for that.
However, I’m wondering if it would be possible to use the face recognition to take roll? Each of my students walk up to the mirror, and the screen gives them a notification when it has marked them as present. Is this a crazy dream?
I currently use a QR system and have students scan their QR “ID badge” on my ipad, but I’d LOVE if they could just walk up to the mirror. I suppose an alternative solution would be a QR reader module that takes attendance. Kids still have to have the QR code, but scanning in on mirror may be easier than my ancient gen 2 ipad.
Anywho, appreciate any input/ideas. Thanks!
@dimpi45 It is very possible. However, keep in mind that prior to identifying faces, the mirror needs to learn/train each kid’s face. This requires taking around 20-50 images (the range is different for each face) of every child which could be a nuisance. I love the idea though!
Hoping that helps.
dimpi45 last edited by
@ronny3050 Oh man, for some reason I was thinking I wouldn’t have to do the training for each student face (hence my giving up on customizing modules based on the student) if I was only taking roll. I don’t know what my brain was doing when I made that poor connection.
Maybe I can start with just one class period and try it out. It seems like it would be a lot of work up front, but could potentially save me a lot of time in the future.
Thanks for the advice!
@dimpi45 That’s precisely how these things are. It takes a long time to set it up, but it reduces time in the future.
Let me know how it goes!
alexyak last edited by
There’s another option to use a cloud service from Microsoft https://www.microsoft.com/cognitive-services/en-us/face-api. It should be enough to have just one good picture of your student uploaded to the server. I’ve got a basic module working that uses these api’s, but it’s not at the stage that I can publish it for everybody yet.