ASLDetect: Arabic sign language detection using ResNet and U-Net like component

Abstract Sign languages are essential for communication among over 430 million deaf and hard-of-hearing individuals worldwide. However, recognizing Arabic Sign Language (ArSL) in real-world settings remains challenging due to issues like background noise, lighting variations, and hand occlusions. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Naif Alasmari, Sultan Asiri
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01588-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850268925823025152
author Naif Alasmari
Sultan Asiri
author_facet Naif Alasmari
Sultan Asiri
author_sort Naif Alasmari
collection DOAJ
description Abstract Sign languages are essential for communication among over 430 million deaf and hard-of-hearing individuals worldwide. However, recognizing Arabic Sign Language (ArSL) in real-world settings remains challenging due to issues like background noise, lighting variations, and hand occlusions. These limitations hinder the effectiveness of existing systems in applications such as assistive technologies and education. To tackle these challenges, we propose ASLDetect, a new model for ArSL recognition that leverages ResNet for feature extraction and a U-Net-based architecture for accurate gesture segmentation. Our method includes preprocessing steps like resizing images to 64 $$\times$$ × 64 pixels, normalization, and selective augmentation to improve robustness in diverse environments. We evaluated ASLDetect on two datasets: ArASL2018, which features plain backgrounds, and ArASL2021, which includes more complex and diverse environments. On ArASL2018, ASLDetect achieved an accuracy of 99.35%, surpassing ResNet34 (99.08%), T-SignSys (97.92%), and UrSL-CNN (0.98%). For ArASL2021, we applied transfer learning from our ArASL2018-trained model, significantly improving performance and reaching 86.84% accuracy-outperforming ResNet34 (82.5%), T-SignSys (58.98%), and UrSL-CNN (0.49%). These results highlight ASLDetect’s accuracy, robustness, and adaptability.
format Article
id doaj-art-1c010a4918cd4f8d8aa4cde35c514766
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1c010a4918cd4f8d8aa4cde35c5147662025-08-20T01:53:19ZengNature PortfolioScientific Reports2045-23222025-05-0115111510.1038/s41598-025-01588-wASLDetect: Arabic sign language detection using ResNet and U-Net like componentNaif Alasmari0Sultan Asiri1Computer Science Department, Applied College, Muhayil, King Khalid UniversityComputer Science Department, Applied College, Muhayil, King Khalid UniversityAbstract Sign languages are essential for communication among over 430 million deaf and hard-of-hearing individuals worldwide. However, recognizing Arabic Sign Language (ArSL) in real-world settings remains challenging due to issues like background noise, lighting variations, and hand occlusions. These limitations hinder the effectiveness of existing systems in applications such as assistive technologies and education. To tackle these challenges, we propose ASLDetect, a new model for ArSL recognition that leverages ResNet for feature extraction and a U-Net-based architecture for accurate gesture segmentation. Our method includes preprocessing steps like resizing images to 64 $$\times$$ × 64 pixels, normalization, and selective augmentation to improve robustness in diverse environments. We evaluated ASLDetect on two datasets: ArASL2018, which features plain backgrounds, and ArASL2021, which includes more complex and diverse environments. On ArASL2018, ASLDetect achieved an accuracy of 99.35%, surpassing ResNet34 (99.08%), T-SignSys (97.92%), and UrSL-CNN (0.98%). For ArASL2021, we applied transfer learning from our ArASL2018-trained model, significantly improving performance and reaching 86.84% accuracy-outperforming ResNet34 (82.5%), T-SignSys (58.98%), and UrSL-CNN (0.49%). These results highlight ASLDetect’s accuracy, robustness, and adaptability.https://doi.org/10.1038/s41598-025-01588-wArabic sign languageClassificationMachine learningImage processingConvolutional neural network.
spellingShingle Naif Alasmari
Sultan Asiri
ASLDetect: Arabic sign language detection using ResNet and U-Net like component
Scientific Reports
Arabic sign language
Classification
Machine learning
Image processing
Convolutional neural network.
title ASLDetect: Arabic sign language detection using ResNet and U-Net like component
title_full ASLDetect: Arabic sign language detection using ResNet and U-Net like component
title_fullStr ASLDetect: Arabic sign language detection using ResNet and U-Net like component
title_full_unstemmed ASLDetect: Arabic sign language detection using ResNet and U-Net like component
title_short ASLDetect: Arabic sign language detection using ResNet and U-Net like component
title_sort asldetect arabic sign language detection using resnet and u net like component
topic Arabic sign language
Classification
Machine learning
Image processing
Convolutional neural network.
url https://doi.org/10.1038/s41598-025-01588-w
work_keys_str_mv AT naifalasmari asldetectarabicsignlanguagedetectionusingresnetandunetlikecomponent
AT sultanasiri asldetectarabicsignlanguagedetectionusingresnetandunetlikecomponent