A Robust Sign Language and Hand Gesture Recognition System Using Convolutional Neural Networks
Saurav Kumar, Pratiyush Kumar, Priyesh Mishra, Pragya Tewari · 2023
Sign language and hand gesture recognition systems have become increasingly important in recent years due to the growing demand for human computer interaction. In this paper, we propose a robust convolutional neural network (CNN)-based system for hand gesture and sign language identification. Using a custom dataset of Indian sign language and hand gestures, our method refines a pre-trained CNN model [1]. On a test set, we assess our system’s performance, and we get a 98.6% accuracy rate. Our research aids in the creation of reliable sign language recognition systems that may be put to practical use in fields like human-computer interaction and assistive technology for deaf and hard-of-hearing people.