How to make a new model?

[wffger]

I used getCurrentPosition() to get the audrey.jpg positions array. The array is too much different from the array in the fack_mask.html. Does the model's position array needed to be trained.
Does the position array determine how the face crop from the image? I saw draw() works well and the yellow polygonal line fits the face faultlessly.

But when I use the array as mask:

[auduno]

If you're planning to get the points to use for a face mask or similar, you might try to use the annotater I released in clmtools (https://github.com/auduno/clmtools), that's what I used. It will probably work getting positions via getCurrentPosition() as well, but these points tend to be a bit imprecise.

[wffger]

I uploaded some pictures.

[auduno]

Yes, the positions array determines how the face is cut out from the image, so you can only use it with that specific image. Did you used a different positions array with this image, or is it the correct one? It looks like it's not aligned correctly.

[wffger]

I used another image. Video still didn't match to the image. I just modified the face_mask.html.

[auduno]

I think I need to see the code to figure out what's wrong here. Do you have the possibility to share an example on dropbox or something similar?