Metraipolis › archive › dc_c595db50bf21
From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts — arXiv:2611.00078
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00078
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:24:25.985Z
- SHA-256 of the archived text
ea032c10483e3e1380649896ed6b3dd366bbc5ebe9b697e95279a7a9feaf9422- Stable URL of this page
https://metraipolis.com/documento/dc_c595db50bf21
How to cite
From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts — arXiv:2611.00078 — arXiv (en), https://arxiv.org/abs/2611.00078 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c595db50bf21 (Metraipolis archive dc_c595db50bf21, sha256 ea032c10483e3e1380649896ed6b3dd366bbc5ebe9b697e95279a7a9feaf9422)
BibTeX
@misc{dcc595db50bf21,
title = {From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts — arXiv:2611.00078},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00078},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c595db50bf21; sha256 ea032c10483e3e1380649896ed6b3dd366bbc5ebe9b697e95279a7a9feaf9422},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00078. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Optical character recognition (OCR) remains inaccessible to many low-resource scripts because annotated document images are unavailable and synthetic training data can fail to preserve script-specific visual structure. We present a data-centric framework that builds end-to-end OCR for such scripts from only an unannotated text corpus and digital fonts, without manually annotating a single training image. A synthetic data engine renders word, line and page images with correct complex-script shaping and automatically derived labels; a YOLOv8 word detector and a convolutional recurrent recognizer trained with connectionist temporal classification learn from these images; and a stage-gate evaluation protocol isolates recognition error before detection is introduced. We demonstrate the framework on Kashmiri, a Perso-Arabic Nastaliq script with approximately 6.8 million speakers that none of six widely used OCR engines supports. Three line-level recognizers, including one transferred from Arabic, stalled between 41% and 79% character error rate (CER), motivating a word-level formulation; subsequent improvements came primarily from rendering fidelity, diacritic-preserving crop margins and tuned non-maximum suppression. The resulting system achieves 0.39% CER on held-out words, 10.0% on synthetic pages and 13.5% on browser-rendered digital pages, and establishes reference results of 18.45% on typeset book pages and 49.8% on degraded historical documents. We publicly release the trained models, the inference code and a synthetic dataset of 285,864 Kashmiri text-line images, and we describe a step-by-step procedure for building OCR for other unsupported scripts. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.00078 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:10:08.007Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).