A DEEP LEARNING APPROACH USING RESNET-50 FOR ARABIC SIGN LANGUAGE RECOGNITION
Boletim da Sociedade Paranaense de Matemática · 16.02.2026 · 44 (5) · 1-9
DOI: 10.5269/bspm.79710 ↗Kurz gefasst
Fachartikel in der Zeitschrift Boletim da Sociedade Paranaense de Matemática, online erschienen am 16.02.2026. Verfasst von Abdelhafid Benyounes und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Arabic Sign Language (ArSL) serves as a vital communication medium for the deaf and hard-of-hearing community within Arabic-speakingregions. However, significant communication barriers often exist between signers and non-signers, limiting access and inclusion. This paper investigates the effectiveness of the ResNet-50 architecture for ArSL recognition. We employ a transfer learning methodology, fine-tuning a ResNet-50 model pre-trained on ImageNet using the RGB Arabic Alphabets Sign Language Dataset containing16,000 images across 32 classes representing the Arabic alphabet. Standard image preprocessing and data augmentation techniques are utilized to enhance model robustness. The study achieves 96% recognition accuracy for static ArSL signs, evaluated using standard classification metrics. This work provides a rigorous evaluation of ResNet-50 within the ArSL context, reinforcing the potential of transfer learning for developing practical assistive communication technologies and promoting greater inclusivity for the Arabic deaf community
Zitieren
APA
Benyounes, A., Bouras, M., Herizi, A., & Ouagueni, F. (2026). A DEEP LEARNING APPROACH USING RESNET-50 FOR ARABIC SIGN LANGUAGE RECOGNITION. Boletim da Sociedade Paranaense de Matemática, 44(5), 1-9. https://doi.org/10.5269/bspm.79710
Vancouver
Benyounes A, Bouras M, Herizi A, Ouagueni F. A DEEP LEARNING APPROACH USING RESNET-50 FOR ARABIC SIGN LANGUAGE RECOGNITION. Boletim da Sociedade Paranaense de Matemática. 2026;44(5):1-9. doi:10.5269/bspm.79710
BibTeX
@article{Benyounes2026,
author = {Benyounes, Abdelhafid and Bouras, Mounir and Herizi, Abdelghafour and Ouagueni, Fayssal},
title = {A DEEP LEARNING APPROACH USING RESNET-50 FOR ARABIC SIGN LANGUAGE RECOGNITION},
journal = {Boletim da Sociedade Paranaense de Matemática},
year = {2026},
volume = {44},
number = {5},
pages = {1--9},
doi = {10.5269/bspm.79710}
}
EUVIMED