Sign language recognition using deep learning through LSTM and CNN

This study presents the application of using deep learning to detect, recognize and translate sign language. Understanding sign language is crucial for communication between the deaf and mute people and the general society. This helps sign language users to easily communicate with others, thus elimi...

Full description

Bibliographic Details
Main Authors: Kiran, Pandian, Mohd Azraai, Mohd Razman, Ismail, Mohd Khairuddin, Muhammad Amirul, Abdullah, Ahmad Fakhri, Ab. Nasir, Wan Hasbullah, Mohd Isa
Format: Article
Language:English
Published: Penerbit UMP 2023
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/38079/
http://umpir.ump.edu.my/id/eprint/38079/1/Sign%20Language%20Recognition%20using%20Deep%20Learning%20through%20LSTM%20and%20CNN.pdf
_version_ 1848825417264267264
author Kiran, Pandian
Mohd Azraai, Mohd Razman
Ismail, Mohd Khairuddin
Muhammad Amirul, Abdullah
Ahmad Fakhri, Ab. Nasir
Wan Hasbullah, Mohd Isa
author_facet Kiran, Pandian
Mohd Azraai, Mohd Razman
Ismail, Mohd Khairuddin
Muhammad Amirul, Abdullah
Ahmad Fakhri, Ab. Nasir
Wan Hasbullah, Mohd Isa
author_sort Kiran, Pandian
building UMP Institutional Repository
collection Online Access
description This study presents the application of using deep learning to detect, recognize and translate sign language. Understanding sign language is crucial for communication between the deaf and mute people and the general society. This helps sign language users to easily communicate with others, thus eliminating the differences between both parties. The objectives of this thesis are to extract features from the dataset for sign language recognition model and the formulation of deep learning models and the classification performance to carry out the sign language recognition. First, we develop methodology for an efficient recognition of sign language. Next is to develop multiple system using three different model which is LSTM, CNN and YOLOv5 and compare the real time test result to choose the best model with the highest accuracy. We used same datasets for all algorithms to determine the best algorithm. The YOLOv5 has achieved the highest accuracy of 97% followed by LSTM and CNN with 94% and 66.67%.
first_indexed 2025-11-15T03:28:35Z
format Article
id ump-38079
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:28:35Z
publishDate 2023
publisher Penerbit UMP
recordtype eprints
repository_type Digital Repository
spelling ump-380792023-07-20T01:28:04Z http://umpir.ump.edu.my/id/eprint/38079/ Sign language recognition using deep learning through LSTM and CNN Kiran, Pandian Mohd Azraai, Mohd Razman Ismail, Mohd Khairuddin Muhammad Amirul, Abdullah Ahmad Fakhri, Ab. Nasir Wan Hasbullah, Mohd Isa QA76 Computer software TJ Mechanical engineering and machinery This study presents the application of using deep learning to detect, recognize and translate sign language. Understanding sign language is crucial for communication between the deaf and mute people and the general society. This helps sign language users to easily communicate with others, thus eliminating the differences between both parties. The objectives of this thesis are to extract features from the dataset for sign language recognition model and the formulation of deep learning models and the classification performance to carry out the sign language recognition. First, we develop methodology for an efficient recognition of sign language. Next is to develop multiple system using three different model which is LSTM, CNN and YOLOv5 and compare the real time test result to choose the best model with the highest accuracy. We used same datasets for all algorithms to determine the best algorithm. The YOLOv5 has achieved the highest accuracy of 97% followed by LSTM and CNN with 94% and 66.67%. Penerbit UMP 2023-04 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/38079/1/Sign%20Language%20Recognition%20using%20Deep%20Learning%20through%20LSTM%20and%20CNN.pdf Kiran, Pandian and Mohd Azraai, Mohd Razman and Ismail, Mohd Khairuddin and Muhammad Amirul, Abdullah and Ahmad Fakhri, Ab. Nasir and Wan Hasbullah, Mohd Isa (2023) Sign language recognition using deep learning through LSTM and CNN. Mekatronika - Journal of Intelligent Manufacturing & Mechatronics, 5 (1). pp. 67-71. ISSN 2637-0883. (Published) https://doi.org/10.15282/mekatronika.v5i1.9410 https://doi.org/10.15282/mekatronika.v5i1.9410
spellingShingle QA76 Computer software
TJ Mechanical engineering and machinery
Kiran, Pandian
Mohd Azraai, Mohd Razman
Ismail, Mohd Khairuddin
Muhammad Amirul, Abdullah
Ahmad Fakhri, Ab. Nasir
Wan Hasbullah, Mohd Isa
Sign language recognition using deep learning through LSTM and CNN
title Sign language recognition using deep learning through LSTM and CNN
title_full Sign language recognition using deep learning through LSTM and CNN
title_fullStr Sign language recognition using deep learning through LSTM and CNN
title_full_unstemmed Sign language recognition using deep learning through LSTM and CNN
title_short Sign language recognition using deep learning through LSTM and CNN
title_sort sign language recognition using deep learning through lstm and cnn
topic QA76 Computer software
TJ Mechanical engineering and machinery
url http://umpir.ump.edu.my/id/eprint/38079/
http://umpir.ump.edu.my/id/eprint/38079/
http://umpir.ump.edu.my/id/eprint/38079/
http://umpir.ump.edu.my/id/eprint/38079/1/Sign%20Language%20Recognition%20using%20Deep%20Learning%20through%20LSTM%20and%20CNN.pdf