American Sign Language Detection and Translation System

Inspiration

The need for inclusivity inspired us to create a tool that closes the communication gap between the Deaf community and hearing individuals. This solution addresses accessibility in education, healthcare, and everyday life.

What it does

The ASL Recognition Assistant translates American Sign Language gestures into text in real-time using computer vision and deep learning, enabling instant communication through a user-friendly interface.

How we built it

We used TensorFlow and Python to train a convolutional neural network (CNN) on a dataset of ASL gestures. The GUI was developed with Tkinter to provide an offline interface.

Challenges we ran into

Key challenges included achieving high accuracy across 29 distinct signs, managing real-time performance on limited hardware - My laptop almost crashed🥲, and ensuring the model works offline.

Accomplishments that we're proud of

Achieved 90.5% accuracy across 29 ASL signs
Developed an offline-capable system for accessibility anywhere
Created a GUI interface to make the tool user-friendly and impactful

What we learned

We deepened our understanding of computer vision, neural network optimization, and GUI. Also, we gained experience in designing solutions that prioritize inclusivity and accessibility.