Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Drawing Recognintion Game with MediaPine

The project is built around drawing and recognizing that drawing.

Demo

Video demo

Predict Table

Predict Table

Table of Contents

About The Project

  • The dataset is taken from Quick Draw. You can get the dataset here
  • This is collected and divided into 2 datasets: train and test. You must be put in data folder.
  • Labels = ['apple', 'cake', 'rabbit', 'fish', 'bread', 'monkey', 'hat', 'elephant', 'bird', 'lion', 'car']

Project structure

├── app
│    └── main.py
├── data
│   ├── test_label.npy
│   ├── test.npy
│   ├── train_label.npy
│   └── train.npy
├── images
│── pie_chart.png
│   ├── pie_chart_test.png
│   ├── pie_chart_train.png
│   ├── PredictTable.png
│   └── video.gif
├── model
│   ├── best_model.pth5
│   └── last_model.pth5
├── README.md
└── src
    ├── dataset.py
    ├── model.py
    ├── test.py
    ├── train.py
    └── visualazation.py

Getting Started

Prerequisites

You need to install the following software on your computer:

  • Python 3.9 or latest
  • pip

Installation

  1. Clone the repository:
git clone https://github.com/alloc110/Drawing-Recognition-Game
cd Drawing-Recognition-Game
  1. Create virtual environment:
python -m venv Drawing-Recognition-Game
  1. Install Packages:
pip install requiretment.txt
  1. Download dataset: After downloading the dataset, put it in the dataset folder.
python src/preprocess.py
  1. Run main.py:
python app/main.py

About

Real-time drawing recognition game using MediaPipe hand tracking and a deep learning model trained on the Google Quick, Draw! dataset.

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages