willjay90 / applefacedetection Goto Github PK

Hello,

I can't save the frame detected.
Is there a method to save the portion of photo detected ?

Thank you

I am trying to use CoreML on the detected faces. My original idea was to capture the image of each detected face and then run that agains the models, but I can't figure out how to get the screenshot of each face. Any hints? I tried using the facebounds in the drawFaceboundingBox method and using that rect to crop the image, but they don't line up.

I want to save an image once the face is detected. But i can't find any solutions for that. Please help

The bounding box around the user's face does not follow him/her correctly. The x position gets reversed somehow. When one moves their face to the left the bounding box goes to the right.

Hi, thank you for a great example!

I'm trying to do this in a smaller view but can´t figure out how to calculate the new Face landmark frames.

Say that I have a smaller AVCaptureVideoPreviewLayer say in a CGRect(x: 0, y: 44, width: 320, height: 300). I get face landmarks like this.

Do you have any idé how I can accomplish this?

hi, if i just want to detect real face, not from image or video( like youtube...), did this lib support that

When changing device orientation (portrait -> landscape, etc.) the detection rectangle is drawn at a wrong position.

hi I'm playing with the vision framework and can use the face landmark feature to get the position of facial features in real time. However, I have to run the detector for every frame. This makes the real time face mask jittery.

any ideas on how we could optimize the landmark detection in a real time feed with only the iOS frameworks?

FYI I tried the object tracker, but it wasn't as impressive as it could be. Maybe you've had better luck?

thanks