Luis Reisewitz

You can use Dlib to detect faces in a static frame as well. This is albeit very slow. Check line 38 and 86 here: https://github.com/zweigraf/face-landmarking-ios/blob/062bf6dabfb1445ddcc1eb7d0344155fee8f4e0b/DisplayLiveSamples/DlibWrapper.mm#L38 This is an old version...

This might have to do with resolution of the camera, I am not sure. I don't have an iPhone 7 to test this here, sorry.

Yes you could return the calculated coordinates from the `doWork` method in DlibWrapper.

If I understand the problem correctly, yes you need some coordinate conversion. In this line: https://github.com/zweigraf/face-landmarking-ios/blob/master/DisplayLiveSamples/SessionHandler.swift#L72 we first convert the metadata object into some other format depending on camera orientation...

There is a function in Dlib called `draw_solid_convex_polygon`. This might work for your needs. You would use this with all points from the detector I guess instead of this code:...

I am not sure if it is zipped already, so that may be worth a try. Also, you can generate your own Dlib model which includes less landmarks and possible...

Well that is a nice improvement, around 20%. If you combine this with a custom model with less landmarks, you could have some nice results.

I did not do that myself yet, so I can only refer you to the Dlib documentation. They talk about this feature [here](http://blog.dlib.net/2014/08/real-time-face-pose-estimation.html) and talk about it in the comments...

Is this in debug mode or with optimizations? Because dlib is very slow in debug mode anyway.

Thanks for your interest in this project. I know what you are talking about with noisy, jumpy. Unfortunately I did not find a solution yet for this problem. What do...