Arabic Sign Language Recognition Using Deep Machine Learning

Wael Suliman; Mohamed Deriche; Hamzah Luqman; Mohamed Mohandes

doi:10.1109/ISAECT53699.2021.9668405

Arabic Sign Language Recognition Using Deep Machine Learning

Wael Suliman, Mohamed Deriche, Hamzah Luqman, Mohamed Mohandes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

In this work, we present an effective method for automatic Arabic Sign Language recognition that uses a Convolutional Neural Network (CNN) for feature extraction and a Long Short-Term Memory (LSTM) for classification. AlexNet, a CNN architecture, is used to extract deep features from the input image while the LSTM is used to preserve the sequential structure of the video frames. The method was tested on a data set consisting of 50 repetitions of 150 signs commonly used in daily activities performed by three signers. The proposed method achieved an overall recognition accuracy of 95.9% for the signer-dependent case, and 43.62% for the more difficult signer-independent case.

Original language	English
Title of host publication	2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665437738
DOIs	https://doi.org/10.1109/ISAECT53699.2021.9668405
State	Published - 2021

Publication series

Name	2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Arabic sign language recognition
CNN
LSTM

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Aerospace Engineering
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/ISAECT53699.2021.9668405

Cite this

Suliman, W., Deriche, M., Luqman, H., & Mohandes, M. (2021). Arabic Sign Language Recognition Using Deep Machine Learning. In 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021 (2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISAECT53699.2021.9668405

Suliman, Wael ; Deriche, Mohamed ; Luqman, Hamzah et al. / Arabic Sign Language Recognition Using Deep Machine Learning. 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021).

@inproceedings{93cb88e583534c5c9e34b373787120b7,

title = "Arabic Sign Language Recognition Using Deep Machine Learning",

abstract = "In this work, we present an effective method for automatic Arabic Sign Language recognition that uses a Convolutional Neural Network (CNN) for feature extraction and a Long Short-Term Memory (LSTM) for classification. AlexNet, a CNN architecture, is used to extract deep features from the input image while the LSTM is used to preserve the sequential structure of the video frames. The method was tested on a data set consisting of 50 repetitions of 150 signs commonly used in daily activities performed by three signers. The proposed method achieved an overall recognition accuracy of 95.9% for the signer-dependent case, and 43.62% for the more difficult signer-independent case.",

keywords = "Arabic sign language recognition, CNN, LSTM",

author = "Wael Suliman and Mohamed Deriche and Hamzah Luqman and Mohamed Mohandes",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.",

year = "2021",

doi = "10.1109/ISAECT53699.2021.9668405",

language = "English",

series = "2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021",

address = "United States",

}

Suliman, W, Deriche, M, Luqman, H & Mohandes, M 2021, Arabic Sign Language Recognition Using Deep Machine Learning. in 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021. 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ISAECT53699.2021.9668405

Arabic Sign Language Recognition Using Deep Machine Learning. / Suliman, Wael; Deriche, Mohamed; Luqman, Hamzah et al.
2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Arabic Sign Language Recognition Using Deep Machine Learning

AU - Suliman, Wael

AU - Deriche, Mohamed

AU - Luqman, Hamzah

AU - Mohandes, Mohamed

PY - 2021

Y1 - 2021

N2 - In this work, we present an effective method for automatic Arabic Sign Language recognition that uses a Convolutional Neural Network (CNN) for feature extraction and a Long Short-Term Memory (LSTM) for classification. AlexNet, a CNN architecture, is used to extract deep features from the input image while the LSTM is used to preserve the sequential structure of the video frames. The method was tested on a data set consisting of 50 repetitions of 150 signs commonly used in daily activities performed by three signers. The proposed method achieved an overall recognition accuracy of 95.9% for the signer-dependent case, and 43.62% for the more difficult signer-independent case.

AB - In this work, we present an effective method for automatic Arabic Sign Language recognition that uses a Convolutional Neural Network (CNN) for feature extraction and a Long Short-Term Memory (LSTM) for classification. AlexNet, a CNN architecture, is used to extract deep features from the input image while the LSTM is used to preserve the sequential structure of the video frames. The method was tested on a data set consisting of 50 repetitions of 150 signs commonly used in daily activities performed by three signers. The proposed method achieved an overall recognition accuracy of 95.9% for the signer-dependent case, and 43.62% for the more difficult signer-independent case.

KW - Arabic sign language recognition

KW - CNN

KW - LSTM

UR - http://www.scopus.com/inward/record.url?scp=85124991497&partnerID=8YFLogxK

U2 - 10.1109/ISAECT53699.2021.9668405

DO - 10.1109/ISAECT53699.2021.9668405

M3 - Conference contribution

AN - SCOPUS:85124991497

T3 - 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021

BT - 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Suliman W, Deriche M, Luqman H , Mohandes M. Arabic Sign Language Recognition Using Deep Machine Learning. In 2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021). doi: 10.1109/ISAECT53699.2021.9668405

Arabic Sign Language Recognition Using Deep Machine Learning

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this