# New Results for the Text Recognition of Arabic Maghrib=i Manuscripts -- Managing an Under-resourced Script

arXiv: https://arxiv.org/abs/2211.16147 · HTML: https://mlsanity.com/paper/2211.16147/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 29 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts](https://mlsanity.com/paper/1907.04041/) (2019)
- [OCR4all -- An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings](https://mlsanity.com/paper/1909.04032/) (2019)
- [Important New Developments in Arabographic Optical Character Recognition (OCR)](https://mlsanity.com/paper/1703.09550/) (2017)
- [Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning](https://mlsanity.com/paper/2201.07661/) (2022)
- [Automated Transcription of Non-Latin Script Periodicals: A Case Study in the Ottoman Turkish Print Archive](https://mlsanity.com/paper/2011.01139/) (2020)
- [Handling Heavily Abbreviated Manuscripts: HTR engines vs text normalisation approaches](https://mlsanity.com/paper/2107.03450/) (2021)

## Built on by (most cited first, 1 of 1)

- [CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition](https://mlsanity.com/paper/2509.19768/) (2025)

## Abstract (arXiv)

HTR models development has become a conventional step for digital humanities projects. The performance of these models, often quite high, relies on manual transcription and numerous handwritten documents. Although the method has proven successful for Latin scripts, a similar amount of data is not yet achievable for scripts considered poorly-endowed, like Arabic scripts. In that respect, we are introducing and assessing a new modus operandi for HTR models development and fine-tuning dedicated to the Arabic Maghrib=i scripts. The comparison between several state-of-the-art HTR demonstrates the relevance of a word-based neural approach specialized for Arabic, capable to achieve an error rate below 5% with only 10 pages manually transcribed. These results open new perspectives for Arabic scripts processing and more generally for poorly-endowed languages processing. This research is part of the development of RASAM dataset in partnership with the GIS MOMM and the BULAC.