Sign Language Recognition based on YOLOv5 Algorithm for the Telugu Sign Language

TL;DR

This paper introduces a YOLOv5-based deep learning model for Telugu Sign Language recognition, achieving high accuracy and efficiency, and demonstrating potential for real-world accessibility applications.

Contribution

It presents a novel application of YOLOv5 with transfer learning for Telugu Sign Language recognition, optimizing parameters for high performance.

Findings

F1-score of 90.5% achieved

Mean Average Precision of 98.1% obtained

Model trained for 200 epochs with balanced accuracy and efficiency

Abstract

Sign language recognition (SLR) technology has enormous promise to improve communication and accessibility for the difficulty of hearing. This paper presents a novel approach for identifying gestures in TSL using the YOLOv5 object identification framework. The main goal is to create an accurate and successful method for identifying TSL gestures so that the deaf community can use slr. After that, a deep learning model was created that used the YOLOv5 to recognize and classify gestures. This model benefited from the YOLOv5 architecture's high accuracy, speed, and capacity to handle complex sign language features. Utilizing transfer learning approaches, the YOLOv5 model was customized to TSL gestures. To attain the best outcomes, careful parameter and hyperparameter adjustment was carried out during training. With F1-score and mean Average Precision (mAP) ratings of 90.5% and 98.1%, the YOLOv5-medium model stands out for its outstanding performance metrics, demonstrating its efficacy in Telugu sign language identification tasks. Surprisingly, this model strikes an acceptable balance between computational complexity and training time to produce these amazing outcomes. Because it offers a convincing blend of accuracy and efficiency, the YOLOv5-medium model, trained for 200 epochs, emerges as the recommended choice for real-world deployment. The system's stability and generalizability across various TSL gestures and settings were evaluated through rigorous testing and validation, which yielded outstanding accuracy. This research lays the foundation for future advancements in accessible technology for linguistic communities by providing a cutting-edge application of deep learning and computer vision techniques to TSL gesture identification. It also offers insightful perspectives and novel approaches to the field of sign language recognition.