Face landmark in smaller AVCaptureVideoPreviewLayer about applefacedetection HOT 2 CLOSED

The VNFaceObservation returns a normalized bounding box. You have to do the math for translation according to size of your layer. For example, I just use the frame.width and frame.height of my Preview.

    func drawFaceWithLandmarks(face: VNFaceObservation) {
    
        let transform = CGAffineTransform(scaleX: 1, y: -1).translatedBy(x: 0, y: -frame.height)
    
        let translate = CGAffineTransform.identity.scaledBy(x: frame.width, y: frame.height)
    
        // The coordinates are normalized to the dimensions of the processed image, with the origin at the image's lower-left corner.
        let facebounds = face.boundingBox.applying(translate).applying(transform)
       ...

from applefacedetection.

I'm still having problem with this and I think its because the videoGravity property I have to change on AVCaptureVideoPreviewLayer.

I made a smaller preview view and changed .videoGravity on videoPreviewLayer

var videoPreviewLayer: AVCaptureVideoPreviewLayer {
   let videoLayer = layer as! AVCaptureVideoPreviewLayer
   videoLayer.videoGravity = .resizeAspectFill
   return videoLayer
}

If you have the time could you please check the changes I made on this fork.
https://github.com/davnag/AppleFaceDetection

from applefacedetection.