Facial Recognition - customize your mirror for every user!

Wilco89

@sarthak18593 I could figure it out myself. But i knew some people already working with this module. So they would know that. Only need to activate my camera now.

Wilco89

All things are working @ the moment just have to start the training but it’s a bit dark at the moment, so i will wait until tomorrow.

KirAsh4

Turn on a light? :)

Wilco89

@KirAsh4 in my coding cave it’s a bit dark :P and totally not the same condition as the kitchen (the place to hang the mirror)

KirAsh4

In that case, you need to go up to the kitchen to grab a beer … and do the training. :)

Wilco89

then the mirror will only recognize when i’m in the kitchen with a beer:P

first off all we need to fix @paviro his PIR Sensor module. When everything is working I can/will create the case and hang it on the wall.
Otherwise my son will destroy it tomorrow morning or my grumpy old cat will play with the cables.

KirAsh4

PIR Sensor module doesn’t work? I don’t know, I don’t have one … never tried it.

Wilco89

When activate it gives a whit screen before startup of the mirror.

KirAsh4

Oh cool, special effects courtesy the PIR sensor … love it. :)

Maybe @paviro should set a delay before activating the sensor reading. I assume that’s wha tit does, like I said, I don’t have a PIR sensor to play with … figured there are enough folks out there doing that already. :)

Wilco89

don’t even got to the MM, after the automatic stat of MM the screen is just white :P

But when @paviro has some time he will defintly look into it.

oder ist das schwierig @paviro ?

KirAsh4

Yeah, I don’t know that module, or where it’s actually failing. But I can imagine if MM is initializing and the sensor is also doing something, things can go wrong. That’s why I suggested a delay.

The touch sensor I’m playing with has a built-in 4 seconds delay before it becomes active, then it spends 5 to (no more than) 10 seconds calibrating itself. So plenty of time for MM to start up completely before the sensor starts “talking” to the rpi.

paviro

@Wilco89 No will do but I have so much stuff on my hand at the moment… Moving to Berlin in August etc…

Wilco89

@paviro wir warten noch ein Moment. Viel Spaß im Berlin.

I hope everything is going well with the move to Berlin. So everybody will be happy in a few weeks.

xdker

why？

^CTraceback (most recent call last):
  File "capture.py", line 35, in <module>
    capture.capture()
  File "/home/pi/MagicMirror/MMM-Facial-Recognition-Tools/facetrainer/lib/capture.py", line 53, in capture
    if is_letter_input('c'):
  File "/home/pi/MagicMirror/MMM-Facial-Recognition-Tools/facetrainer/lib/capture.py", line 23, in is_letter_input
    input_char = raw_input()
KeyboardInterrupt

Note from admin: Please use Markdown on shell snippets!

xdker

This post is deleted!

paviro

Looks like you terminated the process by pressing ctrl-C or strg-C, just press c and then enter and no other key with the c.

xdker

@paviro
Oh sorry, I’m sorry I didn’t notice.
But there are the following tips.
where is capture.pgm not in the name of the folder.

Could not detect single face!  Check the image in capture.pgm to see what was captured and try again with only one face visible.

plumcraft

Hi everyone,

I have the same issue.

What do you want to do?
[1] Capture training images from webcam
[2] Convert ‘*.jpg’ pictures from other cameras to training images
–> 1

Enter the name of the person you want to capture or convert images for.
–> olifier
Images will be placed in ./training_data/olifier

Starting process…

Capturing positive training images.
Type c (and press enter) to capture an image.
Press Ctrl-C to quit.

c
Capturing image…
Could not detect single face! Check the image in capture.pgm to see what was captured and try again with only one face visible.

Thanks a lot

sarthak18593

@plumcraft Are you using the Pi camera module or a usb webcam ?

plumcraft

@sarthak18593

I’m using the pi camera module. It’s correctly enable from the raspi config tool.