Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/cyanosite/iface

Facial Attribute Recognition with CoreML model, written for demonstrational purposes
https://github.com/cyanosite/iface

computer-vision coreml facial-recognition ios machine-learning swiftui

Last synced: 9 days ago
JSON representation

Facial Attribute Recognition with CoreML model, written for demonstrational purposes

Awesome Lists containing this project

README

        

# iFace - Facial Attribute Recognition Demo App

## Description
iFace is a demo iOS app that showcases a Facial Attribute Recognition machine learning model. The app enables users to align their face with the camera view, upon which the model analyzes and determines their facial attributes. The process can be halted by double-tapping on the camera view.

## Features
- Capture real-time data from the camera
- Predict various facial attributes using the machine learning model
- Display the predicted attributes

## Installation
1. Clone the repository from GitHub:
```bash
git clone https://github.com/your-username/your-repo.git
```

2. Open the project in Xcode:
```bash
cd iFace
open iFace.xcodeproj
```

3. Build and run the app on the iOS Simulator or your physical device.

## Usage
1. Launch the app on your iOS device.
2. Position your face within the circle.
3. Wait for the app to process the image and predict the facial attributes.
4. View the predicted attributes.
5. Stop predictions with a double-tap on the camera view.

## Model
The Facial Attribute Recognition machine learning model used in this app is available on [GitHub](https://github.com/Cyanosite/Facial-Attribute-Recognition).

## Contributing
Contributions are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request.

## License
This project is licensed under the [MIT License](LICENSE).

## Contact
For any questions or inquiries, please contact me at [email protected].