Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

HATFormer: Historic Handwritten Arabic Text Recognition with Transformers

Domaine:

natural language processing

Type de record:

papermodel
Créateur:
ChaMijSaeWon
Hôte:avatar
Arabic handwritten text recognition (HTR) is challenging, especially for historical texts, due to diverse writing styles and the intrinsic features of Arabic script. Additionally, Arabic handwriting datasets are smaller compared to English ones, making it difficult to train generalizable Arabic HTR models. To address these challenges, we propose HATFormer, a transformer-based encoder-decoder architecture that builds on a state-of-the-art English HTR model. By leveraging the transformer's attention mechanism, HATFormer captures spatial contextual information to address the intrinsic challenges of Arabic script through differentiating cursive characters, decomposing visual representations, and identifying diacritics. Our customization to historical handwritten Arabic includes an image processor for effective ViT information preprocessing, a text tokenizer for compact Arabic text representation, and a training pipeline that accounts for a limited amount of historic Arabic handwriting data. HATFormer achieves a character error rate (CER) of 8.6% on the largest public historical handwritten Arabic dataset, with a 51% improvement over the best baseline in the literature. HATFormer also attains a comparable CER of 4.2% on the largest private non-historical dataset. Our work demonstrates the feasibility of adapting an English HTR method to a low-resource language with complex, language-specific challenges, contributing to advancements in document digitization, information retrieval, and cultural preservation.

Visit

arxiv.org

Tasks

computer visionoptical character recognition

Tags

Computer Vision and Pattern RecognitionComputation and LanguageMachine Learning

Similaires

End-Shape Recognition for Arabic Handwritten Text SegmentationImproving Arabic handwritten text recognition through transfer learning with convolutional neural network-based modelsKHATT: Handwritten Arabic TextAjami Handwritten Text Recognition DatasetArabic Handwritten Text Line Datasetolajesu907/Yoruba-language-handwritten-text-recognition-system

End-Shape Recognition for Arabic Handwritten Text Segmentation

Improving Arabic handwritten text recognition through transfer learning with convolutional neural network-based models

Arabic handwritten text recognition is a complex and challenging research domain. This study propose

KHATT: Handwritten Arabic Text

Introduction


KHATT: Handwritten Arabic Text was developed by

Ajami Handwritten Text Recognition Dataset

Technical Details

This dataset contains i

Arabic Handwritten Text Line Dataset

Segmentation of Arabic manuscripts into lines of text and words is an important step to make recogni

olajesu907/Yoruba-language-handwritten-text-recognition-system