International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Sign language recognition model (camera recognition to speech) Tushar Surwade1, Vrushali Wankhede2, suraj Menon 3, Dipti Mondal4, Ritesh Kakade5, Sanket Pawar6 1,2,3,4,5,6Computer Engineering Department, Keystone School of Engineering, Pune, Maharashtra, India.
---------------------------------------------------------------------***-------------------------------------------------------------------Key Words: Sign language recognition, deep learning, Abstract:
computer vision, natural language processing, gesture detection, hand tracking, real-time processing, accessibility.
Sign language is a primary mode of communication for the deaf and hard of hearing community. Despite its importance, there exists a communication gap between sign language users and non-signers, hindering effective interaction and accessibility. In this research, we propose a novel deep learning-based framework for real-time sign language recognition, aiming to bridge this communication barrier.
1. INTRODUCTION: Sign language plays a crucial role in enabling communication for the deaf and hard of hearing community. However, a communication gap persists between sign language users and non-signers. This research proposes a deep learning-based framework for real-time sign language recognition, aiming to bridge this gap. By leveraging advancements in computer vision and natural language processing, our framework translates sign language gestures captured by a camera into spoken language. We address challenges such as gesture variability and environmental factors to develop a reliable and efficient system. Through this work, we aim to enhance accessibility and inclusivity for individuals who rely on sign language.
Our approach leverages recent advancements in computer vision and natural language processing to translate sign language gestures captured through a camera into spoken language. We employ convolutional neural networks (CNNs) for hand gesture detection and tracking, allowing robust recognition of dynamic hand movements and configurations. Additionally, we utilize recurrent neural networks (RNNs) or transformer models to encode temporal dependencies and extract meaningful features from the gesture sequences.
2. SYSTEM ARCHITECHTURE
To evaluate the effectiveness of our proposed framework, we conduct extensive experiments on publicly available sign language datasets, including both isolated and continuous sign sequences. We compare the performance of our model against existing methods, demonstrating superior accuracy and realtime processing capabilities. Furthermore, we evaluate the generalization of our model across different sign languages and variations in lighting conditions, background clutter, and signer demographics.
The sign language recognition system comprises several interconnected modules designed to seamlessly translate sign language gestures into spoken language. The architecture consists of three main components: Input Module, Deep Learning Model, and Output Module. 1.
Our results indicate promising outcomes in real-world scenarios, showcasing the potential of our approach to enhance accessibility and facilitate seamless communication between sign language users and nonsigners. This research contributes to the advancement of assistive technologies and lays the foundation for future developments in sign language recognition systems. Keywords: Sign language recognition, deep learning, computer vision, natural language processing, g
© 2024, IRJET
|
Impact Factor value: 8.226
|
Input Module:
The Input Module captures sign language gestures using a camera or other input devices.
Preprocessing techniques are applied to enhance the quality of the input data, such as noise reduction and normalization.
Feature extraction methods may be employed to represent the spatial and temporal characteristics of the gestures effectively.
ISO 9001:2008 Certified Journal
|
Page 405