https://github.com/NovatecConsulting/FaceRecognition-in-ARKit

Detects faces using the Vision-API and runs the extracted face through a CoreML-model to identiy the specific persons.
https://github.com/NovatecConsulting/FaceRecognition-in-ARKit

arkit coreml face-recognition ios machine-learning

Last synced: 3 months ago
JSON representation

Detects faces using the Vision-API and runs the extracted face through a CoreML-model to identiy the specific persons.

• Host: GitHub
• URL: https://github.com/NovatecConsulting/FaceRecognition-in-ARKit
• Owner: NovatecConsulting
• License: mit
• Created: 2017-09-03T06:38:58.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-14T09:04:22.000Z (over 6 years ago)
• Last Synced: 2024-06-03T23:45:51.268Z (5 months ago)
• Topics: arkit, coreml, face-recognition, ios, machine-learning
• Language: Swift
• Size: 11.4 MB
• Stars: 832
• Watchers: 41
• Forks: 114
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# FaceRecognition in ARKit

This is a simple showcase project, that detects faces using the Vision-API and runs the extracted face through a CoreML-model to identiy the specific persons.

![image of scene with face recognition](demo.gif)

## Requirements

* Xcode 9

* iPhone 6s or newer

* Machine-Learning model

## Machine-Learning model

To create your own machine-learning model, you can read our blog post ["How we created our Face-Recognition model"](https://blog.novatec-gmbh.de/created-face-recognition-model/)

The short version is:

* We trained a model in the AWS using Nvidia DIGITS

* Took a couple of hundred pictures of each person, and extracted the faces

* Also added an "unknown" category with differnent faces.

* Used a pretrained model fine-tuned for face-recognition.

## Acknowledgements

* [3D-Text](https://github.com/hanleyweng/CoreML-in-ARKit)