https://github.com/vintellx/gesture2text
Real Time Hand Signs Recognition using CNN and LSTM Model.
https://github.com/vintellx/gesture2text
cnn gesture-detection gesture-recognition handsign lstm realtime
Last synced: 5 months ago
JSON representation
Real Time Hand Signs Recognition using CNN and LSTM Model.
- Host: GitHub
- URL: https://github.com/vintellx/gesture2text
- Owner: VintellX
- License: gpl-3.0
- Created: 2024-06-04T12:22:56.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-08-09T01:29:02.000Z (over 1 year ago)
- Last Synced: 2025-02-19T07:33:48.343Z (11 months ago)
- Topics: cnn, gesture-detection, gesture-recognition, handsign, lstm, realtime
- Language: Jupyter Notebook
- Homepage:
- Size: 143 KB
- Stars: 0
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Gesture2Text: An Image Processing Approach Using LSTM & CNN Models
This repository contains the code and resources for our project on comparing Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models for hand gesture recognition and converting them into text.
## Installation
To get started with this project, clone the repository and install the necessary dependencies.
```bash
git clone "https://github.com/VintellX/Gesture2Text.git"
pip3 install -r requirements.txt
```
## Model Architechture
The project consists of two models:
- [CNN Model](./CNN_Model.ipynb)
- [LSTM Model](./LSTM_Model.ipynb)
### CNN
The Convolutional Neural Network (CNN) model extracts spatial features from images using multiple convolutional layers, pooling layers, fully connected layers, and an output layer.
### LSTM
The Long Short-Term Memory (LSTM) model processes sequences of spatial features extracted from image sequences, capturing temporal dependencies with LSTM layers.
## License
This project is licensed under the [GNU General Public License v3.0](./LICENSE).