Sensor fusion of motion-based sign language interpretation with deep learning

Sign language was designed to allow hearing-impaired people to interact with others. Nonetheless, knowledge of sign language is uncommon in society, which leads to a communication barrier with the hearing-impaired community. Many studies of sign language recognition ut...

Full description

Bibliographic Details
Main Authors: Lee, Boon Giin, Chong, Teak-Wei, Chung, Wan-Young
Format: Article
Language:English
Published: MDPI AG 2020
Subjects:
Online Access:https://eprints.nottingham.ac.uk/63821/
_version_ 1848800061657448448
author Lee, Boon Giin
Chong, Teak-Wei
Chung, Wan-Young
author_facet Lee, Boon Giin
Chong, Teak-Wei
Chung, Wan-Young
author_sort Lee, Boon Giin
building Nottingham Research Data Repository
collection Online Access
description Sign language was designed to allow hearing-impaired people to interact with others. Nonetheless, knowledge of sign language is uncommon in society, which leads to a communication barrier with the hearing-impaired community. Many studies of sign language recognition utilizing computer vision (CV) have been conducted worldwide to reduce such barriers. However, this approach is restricted by the visual angle and highly affected by environmental factors. In addition, CV usually involves the use of machine learning, which requires collaboration of a team of experts and utilization of high-cost hardware utilities; this increases the application cost in real-world situations. Thus, this study aims to design and implement a smart wearable American Sign Language (ASL) interpretation system using deep learning, which applies sensor fusion that “fuses” six inertial measurement units (IMUs). The IMUs are attached to all fingertips and the back of the hand to recognize sign language gestures; thus, the proposed method is not restricted by the field of view. The study reveals that this model achieves an average recognition rate of 99.81% for dynamic ASL gestures. Moreover, the proposed ASL recognition system can be further integrated with ICT and IoT technology to provide a feasible solution to assist hearing-impaired people in communicating with others and improve their quality of life.
first_indexed 2025-11-14T20:45:34Z
format Article
id nottingham-63821
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:45:34Z
publishDate 2020
publisher MDPI AG
recordtype eprints
repository_type Digital Repository
spelling nottingham-638212020-11-18T01:18:35Z https://eprints.nottingham.ac.uk/63821/ Sensor fusion of motion-based sign language interpretation with deep learning Lee, Boon Giin Chong, Teak-Wei Chung, Wan-Young Sign language was designed to allow hearing-impaired people to interact with others. Nonetheless, knowledge of sign language is uncommon in society, which leads to a communication barrier with the hearing-impaired community. Many studies of sign language recognition utilizing computer vision (CV) have been conducted worldwide to reduce such barriers. However, this approach is restricted by the visual angle and highly affected by environmental factors. In addition, CV usually involves the use of machine learning, which requires collaboration of a team of experts and utilization of high-cost hardware utilities; this increases the application cost in real-world situations. Thus, this study aims to design and implement a smart wearable American Sign Language (ASL) interpretation system using deep learning, which applies sensor fusion that “fuses” six inertial measurement units (IMUs). The IMUs are attached to all fingertips and the back of the hand to recognize sign language gestures; thus, the proposed method is not restricted by the field of view. The study reveals that this model achieves an average recognition rate of 99.81% for dynamic ASL gestures. Moreover, the proposed ASL recognition system can be further integrated with ICT and IoT technology to provide a feasible solution to assist hearing-impaired people in communicating with others and improve their quality of life. MDPI AG 2020-11-02 Article PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/63821/1/Lee-2020-Sensor-fusion-of-motion-based-sign-.pdf Lee, Boon Giin, Chong, Teak-Wei and Chung, Wan-Young (2020) Sensor fusion of motion-based sign language interpretation with deep learning. Sensors, 20 (21). p. 6256. ISSN 1424-8220 deep learning; human-computer interaction; motion sensor; sensor fusion; sign language recognition; wearable computing http://dx.doi.org/10.3390/s20216256 doi:10.3390/s20216256 doi:10.3390/s20216256
spellingShingle deep learning; human-computer interaction; motion sensor; sensor fusion; sign language recognition; wearable computing
Lee, Boon Giin
Chong, Teak-Wei
Chung, Wan-Young
Sensor fusion of motion-based sign language interpretation with deep learning
title Sensor fusion of motion-based sign language interpretation with deep learning
title_full Sensor fusion of motion-based sign language interpretation with deep learning
title_fullStr Sensor fusion of motion-based sign language interpretation with deep learning
title_full_unstemmed Sensor fusion of motion-based sign language interpretation with deep learning
title_short Sensor fusion of motion-based sign language interpretation with deep learning
title_sort sensor fusion of motion-based sign language interpretation with deep learning
topic deep learning; human-computer interaction; motion sensor; sensor fusion; sign language recognition; wearable computing
url https://eprints.nottingham.ac.uk/63821/
https://eprints.nottingham.ac.uk/63821/
https://eprints.nottingham.ac.uk/63821/