Deep Learning Based Web Application for Hand Sign Recognition

Computer Engineering

The goal of this project is to create a web application powered by deep learning that can accurately identify and interpret alphabets from American Sign Language (ASL). For individuals who are unable to hear or speak, sign language serves as their primary means of communication. It is one of the oldest and most intuitive languages used to convey thoughts and emotions. However, since the majority of people are unfamiliar with sign language and trained interpreters are often not readily available, we have developed a real-time recognition system powered by neural networks. This project introduces an innovative approach to recognizing sign language alphabets. By leveraging computer vision and deep learning techniques, our system can interpret hand gestures and translate them into corresponding alphabet letters. The process begins by applying a filter to isolate the hand from the background. Once filtered, the image is processed by a classifier that determines which letter the hand gesture represents.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.