Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques

In recent years, the role of pattern recognition in systems based on human computer interaction (HCI) has spread in terms of computer vision applications and machine learning, and one of the most important of these applications is to recognize the hand gestures used in dealing with deaf people, in p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gamal Tharwat, Abdelmoty M. Ahmed, Belgacem Bouallegue
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer engineering. Computer hardware TK7885-7895
Acceso en línea:	https://doaj.org/article/e81428d5acd448d28a7e3b173872ae23
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e81428d5acd448d28a7e3b173872ae23
record_format	dspace
spelling	oai:doaj.org-article:e81428d5acd448d28a7e3b173872ae232021-11-08T02:35:16ZArabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques2090-015510.1155/2021/2995851https://doaj.org/article/e81428d5acd448d28a7e3b173872ae232021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/2995851https://doaj.org/toc/2090-0155In recent years, the role of pattern recognition in systems based on human computer interaction (HCI) has spread in terms of computer vision applications and machine learning, and one of the most important of these applications is to recognize the hand gestures used in dealing with deaf people, in particular to recognize the dashed letters in surahs of the Quran. In this paper, we suggest an Arabic Alphabet Sign Language Recognition System (AArSLRS) using the vision-based approach. The proposed system consists of four stages: the stage of data processing, preprocessing of data, feature extraction, and classification. The system deals with three types of datasets: data dealing with bare hands and a dark background, data dealing with bare hands, but with a light background, and data dealing with hands wearing dark colored gloves. AArSLRS begins with obtaining an image of the alphabet gestures, then revealing the hand from the image and isolating it from the background using one of the proposed methods, after which the hand features are extracted according to the selection method used to extract them. Regarding the classification process in this system, we have used supervised learning techniques for the classification of 28-letter Arabic alphabet using 9240 images. We focused on the classification for 14 alphabetic letters that represent the first Quran surahs in the Quranic sign language (QSL). AArSLRS achieved an accuracy of 99.5% for the K-Nearest Neighbor (KNN) classifier.Gamal TharwatAbdelmoty M. AhmedBelgacem BouallegueHindawi LimitedarticleComputer engineering. Computer hardwareTK7885-7895ENJournal of Electrical and Computer Engineering, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer engineering. Computer hardware TK7885-7895
spellingShingle	Computer engineering. Computer hardware TK7885-7895 Gamal Tharwat Abdelmoty M. Ahmed Belgacem Bouallegue Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques
description	In recent years, the role of pattern recognition in systems based on human computer interaction (HCI) has spread in terms of computer vision applications and machine learning, and one of the most important of these applications is to recognize the hand gestures used in dealing with deaf people, in particular to recognize the dashed letters in surahs of the Quran. In this paper, we suggest an Arabic Alphabet Sign Language Recognition System (AArSLRS) using the vision-based approach. The proposed system consists of four stages: the stage of data processing, preprocessing of data, feature extraction, and classification. The system deals with three types of datasets: data dealing with bare hands and a dark background, data dealing with bare hands, but with a light background, and data dealing with hands wearing dark colored gloves. AArSLRS begins with obtaining an image of the alphabet gestures, then revealing the hand from the image and isolating it from the background using one of the proposed methods, after which the hand features are extracted according to the selection method used to extract them. Regarding the classification process in this system, we have used supervised learning techniques for the classification of 28-letter Arabic alphabet using 9240 images. We focused on the classification for 14 alphabetic letters that represent the first Quran surahs in the Quranic sign language (QSL). AArSLRS achieved an accuracy of 99.5% for the K-Nearest Neighbor (KNN) classifier.
format	article
author	Gamal Tharwat Abdelmoty M. Ahmed Belgacem Bouallegue
author_facet	Gamal Tharwat Abdelmoty M. Ahmed Belgacem Bouallegue
author_sort	Gamal Tharwat
title	Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques
title_short	Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques
title_full	Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques
title_fullStr	Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques
title_full_unstemmed	Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques
title_sort	arabic sign language recognition system for alphabets using machine learning techniques
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/e81428d5acd448d28a7e3b173872ae23
work_keys_str_mv	AT gamaltharwat arabicsignlanguagerecognitionsystemforalphabetsusingmachinelearningtechniques AT abdelmotymahmed arabicsignlanguagerecognitionsystemforalphabetsusingmachinelearningtechniques AT belgacembouallegue arabicsignlanguagerecognitionsystemforalphabetsusingmachinelearningtechniques
_version_	1718443321603391488

Arabic Sign Language Recognition System for Alphabets Using Machine Learning Techniques

Ejemplares similares