Hand and Sign Recognition of Alphabets Using YOLOv5

• Published in: SN computer science Vol. 5; no. 3; p. 311
• Main Authors: Poornima, I. Gethzi Ahila, Priya, G. Sakthi, Yogaraja, C. A., Venkatesh, R., Shalini, P.
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 09.03.2024; Springer Nature B.V
• Subjects: Advances in Computational Approaches for Image Processing; Algorithms; Alphabets; Classification; Cloud Applications and Network Security; Communication; Computer Imaging; Computer Science; Computer Systems Organization and Communication Networks; Data Structures and Information Theory; Datasets; Deep learning; Fingers; Information Systems and Communication Service; Machine learning; Neural networks; Object recognition; Original Research; Pattern Recognition and Graphics; Sign language; Software Engineering/Programming and Operating Systems; Vision; Wireless Networks; ASL hand gesture; Sign recognition; Hand gesture; Object detection; YOLO5
• ISSN: 2661-8907; 2662-995X; 2661-8907
• DOI: 10.1007/s42979-024-02628-4

Deaf and dumb people who apply visual gestures can communicate using hand, facial, and body gestures. As there are various ways to communicate but still no compatible technologies available that aid in linking this group of deaf and dumb people to the rest of the people in the world, one of the main forms of communication among them is hand gestures. With the use of picture classification and machine learning, computers can understand sign language, which can subsequently be translated by humans. Finger sign alphabets are a fundamental part of learning sign language. This work primarily focuses on teaching American alphabet sign languages, which is the foundational stage for teaching hand gestures. YOLO (You Only Look Once) version 5 is used aimed at this kind of object recognition. The majority of current technologies involve machine learning algorithms, CNN algorithms, and electromyography approaches; however, they fall short of Yolo's level of accuracy. Yolo v5 has been proved to be better than its previous version in terms of both accuracy and speed.