Salvato in:
Dettagli Bibliografici
Autori principali: Boufenar, Chaouki, Rabiai, Mehdi Ayoub, Zahaf, Boualem Nadjib, Ouaras, Khelil Rafik
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.15023
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916656754720768
author Boufenar, Chaouki
Rabiai, Mehdi Ayoub
Zahaf, Boualem Nadjib
Ouaras, Khelil Rafik
author_facet Boufenar, Chaouki
Rabiai, Mehdi Ayoub
Zahaf, Boualem Nadjib
Ouaras, Khelil Rafik
contents Handwritten Arabic script recognition is a challenging task due to the script's dynamic letter forms and contextual variations. This paper proposes a hybrid approach combining convolutional neural networks (CNNs) and Transformer-based architectures to address these complexities. We evaluated custom and fine-tuned models, including EfficientNet-B7 and Vision Transformer (ViT-B16), and introduced an ensemble model that leverages confidence-based fusion to integrate their strengths. Our ensemble achieves remarkable performance on the IFN/ENIT dataset, with 96.38% accuracy for letter classification and 97.22% for positional classification. The results highlight the complementary nature of CNNs and Transformers, demonstrating their combined potential for robust Arabic handwriting recognition. This work advances OCR systems, offering a scalable solution for real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15023
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging the Gap: Fusing CNNs and Transformers to Decode the Elegance of Handwritten Arabic Script
Boufenar, Chaouki
Rabiai, Mehdi Ayoub
Zahaf, Boualem Nadjib
Ouaras, Khelil Rafik
Computer Vision and Pattern Recognition
Handwritten Arabic script recognition is a challenging task due to the script's dynamic letter forms and contextual variations. This paper proposes a hybrid approach combining convolutional neural networks (CNNs) and Transformer-based architectures to address these complexities. We evaluated custom and fine-tuned models, including EfficientNet-B7 and Vision Transformer (ViT-B16), and introduced an ensemble model that leverages confidence-based fusion to integrate their strengths. Our ensemble achieves remarkable performance on the IFN/ENIT dataset, with 96.38% accuracy for letter classification and 97.22% for positional classification. The results highlight the complementary nature of CNNs and Transformers, demonstrating their combined potential for robust Arabic handwriting recognition. This work advances OCR systems, offering a scalable solution for real-world applications.
title Bridging the Gap: Fusing CNNs and Transformers to Decode the Elegance of Handwritten Arabic Script
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15023