0

I've been playing with Apple's CoreML and Vision APIs.

My goal would be to make a simple proof of concept and be able to recognize nails on a hand picture. This is very specific.

I have been trying to find documentation on how to create your own VNRequest, and I really have no idea on how to do this.

I know that the Vision API offers rectangle, face and text recognition only...

How can I make my own request to teach Vision how to recognize what I want on a picture ?

Scaraux
  • 3,841
  • 4
  • 40
  • 80

1 Answers1

1

You will have to create (or find) a Core ML model that can do this. There is at least one open source model that can detect nails, so you'd have to convert this to Core ML. And then you use VNCoreMLRequest to run this model using Vision.

Matthijs Hollemans
  • 7,706
  • 2
  • 16
  • 23