Metraipolis › archive › dc_0e7203370bc1
Benchmarking Vision-Language Models for Urdu Nastaliq Handwriting Recognition — arXiv:2611.01635
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01635
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:18:05.646Z
- SHA-256 of the archived text
ba838db8ac0902bdbd5e6f4b789bb83352c82da0378d5409788fc1b0e64d24d8- Stable URL of this page
https://metraipolis.com/documento/dc_0e7203370bc1
How to cite
Benchmarking Vision-Language Models for Urdu Nastaliq Handwriting Recognition — arXiv:2611.01635 — arXiv (en), https://arxiv.org/abs/2611.01635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e7203370bc1 (Metraipolis archive dc_0e7203370bc1, sha256 ba838db8ac0902bdbd5e6f4b789bb83352c82da0378d5409788fc1b0e64d24d8)
BibTeX
@misc{dc0e7203370bc1,
title = {Benchmarking Vision-Language Models for Urdu Nastaliq Handwriting Recognition — arXiv:2611.01635},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01635},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e7203370bc1; sha256 ba838db8ac0902bdbd5e6f4b789bb83352c82da0378d5409788fc1b0e64d24d8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Handwritten Urdu is hard to recognize because the cursive Nastaliq script has no fixed baseline and no clear character boundaries. We benchmark six systems on the Urdu Nastaliq Handwritten Dataset (UNHD): Tesseract (default configuration), a script-specific recognizer trained on printed Urdu (UTRNet-Large), two open-source vision-language models (VLMs), and two commercial VLMs. All six systems are evaluated without fine-tuning on 2,465 single-line images (Part A), and the four VLMs receive the same fixed prompt (decoding uses temperature 0 where configurable, except for Claude Sonnet 5, whose decoding cannot be configured). Both commercial VLMs reach lower error than the printed-Urdu recognizer and the open-source VLMs. We do not compare against handwriting-trained recognizers, which would likely do better in-domain; we characterize zero-shot behavior, not state of the art. We also describe three distinct failure modes among the ranked systems. In one of them, a commercial model explicitly declines to transcribe a few very hard-to-read images instead of guessing. In a second study (Part B), VLMs correct the output of a separate OCR system using both the source image and the noisy text. Once separated from each model's own reading ability, the benefit is small on Tesseract's output (0.7% to 7.4%) and larger (17.9% and 21.9%) only for the two commercial correctors given UTRNet's text. It appears to depend on how legible the supplied text already is, and a weaker corrector can make a more legible text worse. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01635 — 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 2026-11-03T18:09:53.613Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).