Ecosyste.ms: Awesome

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

Awesome Lists | Featured Topics | Projects

https://github.com/marcpinet/handigits

🖐️ Background-independent deep learning model for hand sign digit recognition, using my own Deep Learning framework! (Neuralnetlib)
https://github.com/marcpinet/handigits

cv2 deep-learning hand keras mediapipe preprocessing recognition tensorflow

Last synced: 19 days ago
JSON representation

🖐️ Background-independent deep learning model for hand sign digit recognition, using my own Deep Learning framework! (Neuralnetlib)

Awesome Lists containing this project

README

        

# Handigits

## 📝 Description

The goal of this project was to make a deep learning model that could recognize hand signs digits, no matter the environment.

> [!TIP]
> NEW: The project now uses [Neuralnetlib, my own deep learning framework](https://github.com/marcpinet/neuralnetlib) instead of TensorFlow and Keras!

Every information you need is in the source code, but here are some important points:

- The dataset used is: [Sign-Language-Digits-Dataset](https://github.com/ardamavi/Sign-Language-Digits-Dataset)
- The library I use to detect the hand is: [mediapipe](https://github.com/google-ai-edge/mediapipe)

I don't think this project deserves a bigger README, like my other projects.

It was primarily made for fun and to learn more about real-time processing and deep learning.

## 🎥 Demo

![demo](resources/demo.gif)

## 💡 How to use

### Prerequisites

* Python 3.7.0+

Get a copy of the Project. Assuming you have git installed, open your Terminal and enter:

```bash
git clone 'https://github.com/marcpinet/handigits'
```

To install all needed requirements run the following command in the project directory:

```bash
pip install -r requirements.txt
```

### Running

After that, you can proceed to start the program by running `main.py`.

## 🐛 Known issues

* Nothing yet!

## 🥅 TO-DO List

* Nothing yet!

## ✍️ Authors

* **Marc Pinet** - *Initial work* - [marcpinet](https://github.com/marcpinet)

## 📃 License

This project is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details