Sanket is a real-time sign language recognition application. It's designed to recognize a variety of sign language gestures, making communication easier for those who use sign language.
-
Real-Time Recognition: Sanket can recognize sign language gestures in real-time, providing instant feedback to the user.
-
Easy-to-Use Interface: The application is designed with simplicity in mind, making it easy for anyone to use.
-
Adaptive Learning: Sanket learns from each interaction, improving its accuracy over time.
-
High Accuracy: Our model is trained on a custom dataset, ensuring high accuracy in gesture recognition.
-
Real Time User Progress Data: Users can track their progress in real-time, helping them improve their sign language skills.
Our model is trained for 26 alphabets and 16 words of American Sign Language (ASL), which are commonly used in general communication.
Front-end:
- React
- Redux
Back-end:
- Firebase (for hosting, authentication, and storage)
Machine Learning Framework:
- MediaPipe
-
Complete Dashboard Feature: We plan to enhance the dashboard feature to provide more detailed progress tracking and user statistics.
-
Sign Language Learning Page: We aim to add a learning page that will serve as a dictionary for sign language. This will help users learn and understand sign language more effectively.
-
More Gestures: We plan to expand the model's capabilities to recognize more gestures, making the application more versatile and useful.
-
User Customization: We aim to add more customization options for users, allowing them to tailor the application to their specific needs.
- Clone the repository using
git clone https://github.com/vitheshshetty00/Sanket.git - Move to the appropriate directory:
cd Sanket - Install dependencies with
npm install - setup firebase by creating a project in firebase and adding the firebase config in
src/firebase.js - Start the server with
npm start - Open http://localhost:3000 to view it in the browser.