Paper Key : IRJ************325
Author: Sanchit Sharma
Date Published: 02 Sep 2024
Abstract
American Sign Language (ASL) is a vital communication method for individuals who are deaf or hard of hearing. However, a significant communication gap exists between ASL users and those who do not understand sign language, leading to challenges in accessibility and inclusivity. This paper presents the development of a real-time, vision-based system capable of recognizing and translating ASL fingerspelling gestures into text. The system leverages Convolutional Neural Networks (CNNs) and various machine learning tools, achieving an accuracy of 98.02% in recognizing the 26 letters of the ASL fingerspelling alphabet. This research offers a cost-effective solution that reduces reliance on interpreters, promoting greater independence and communication for the deaf and mute (D&M) community.