A POC showing how to create a Iphone App with CoreML that recognizes the MNIST numbers.


How to go from MNIST to a full CoreML app on your iPhoneX

  • What is the purpose of this POC: It shows how one can build a CoreML model for Iphone X that will recognize handwritten numbers.

Link to DEMO or 30s VIDEO of the project


  • What is the benefit for the customer: A user of such an app can recgnize things on his mobile phone without having to send the data to the server for processing. This might be relevant for apps that need a fast object recognition, or don't want to send to much data around.
  • What is the benefit for the business: The business owner might save a lot of money doing the recognition on the phone instead of on the server. Also faster response times.


  • How much MD did you use to build it: 8MD.


  • Which data is it based on: MNIST dataset (open source)

Used Technologies

  • Which technologies were used: CoreML, Keras


  • Which things could be build with this POC if you had more time: Build a CoreML model for something where it actually makes sense to use the detection on the mobile device.