Enhancing Sign Language Recognition Using Deep Convolutional Neural Networks
Athanasios Kanavos, Orestis Papadimitriou, Phivos Mylonas, Manolis Μaragoudakis
Abstract
The advancements in sensing technologies and AI algorithms have opened up a wide range of possibilities for developing applications to meet the needs of individuals who are deaf or hard of hearing. Sign language plays a vital role in the lives of people with hearing and speaking disabilities. This research aims to explore digital image processing and machine learning methods for efficiently building a sign language dataset and creating a sign language interface system. The proposed system utilizes a Convolutional Neural Network (CNN) to analyze and interpret hand gestures and poses, converting them into natural language. The developed CNN model specifically focuses on improving the accuracy of predicting the American Sign Language alphabet. Despite variations in dataset conditions and size, the model achieved an exceptional accuracy rate of 98.73%. Additionally, it demonstrated a low loss value of 0.0539, indicating its robust performance.