EE 541 – A Computational Introduction to Deep Learning : FALL 2024

CV for American Sign Language Detection

This repository contains the code for a web application built with TensorFlow and Gradio for interactive American Sign Language (ASL) gesture recognition. The application allows users to upload images or use real-time webcam input to detect ASL gestures and provides predictions with confidence scores.

In addition to the web application, the repository also includes a Jupyter notebook that performs a comparative study on different benchmark Computer Vision (CV) models. This analysis aims to evaluate the performance of various models for ASL recognition, helping to determine the best model for real-time hand gesture classification.

Predicted Outputs from Gradio :

A short video was recorded on the Gradio Web Application and the same video was processed for prediction.

License

This project is licensed under the MIT License - see the LICENSE file for details.