Metraipolis › archive › dc_fed4481aafa8
A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations — arXiv:2609.33449
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33449
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:40:01.403Z
- SHA-256 of the archived text
bbe792c18d939ec6f94845c8e290958af9cda23dd32b0342f84459da7e802b73- Stable URL of this page
https://metraipolis.com/documento/dc_fed4481aafa8
How to cite
A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations — arXiv:2609.33449 — arXiv (en), https://arxiv.org/abs/2609.33449 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fed4481aafa8 (Metraipolis archive dc_fed4481aafa8, sha256 bbe792c18d939ec6f94845c8e290958af9cda23dd32b0342f84459da7e802b73)
BibTeX
@misc{dcfed4481aafa8,
title = {A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations — arXiv:2609.33449},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33449},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fed4481aafa8; sha256 bbe792c18d939ec6f94845c8e290958af9cda23dd32b0342f84459da7e802b73},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33449. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Historical manuscript illustrations preserve rich visual evidence of past cultures. They depict people, animals, plants, diagrams, music notations, and decorative forms. Although large digitization projects have made many manuscripts available online, the material itself remains difficult to explore at scale. Extraction systems can find illustrations on manuscript pages, but without meaningful categories, large collections remain hard to search and explore. We address this gap by introducing a manually labeled dataset of 15,000 illustrations from manuscripts dating back hundreds of years across 22 categories, and evaluating modern vision models for image classification on this task. The problem is challenging due to stylistic diversity, degradation, and semantic ambiguity, with many images that fit more than one category. We compare fine-tuned CNN and Transformer-based classifiers, zero-shot CLIP, embedding-based classifiers, and direct vision-language models. Results show that fine-tuned image classifiers perform best overall, with ConvNeXt reaching 88.9% accuracy and 81.3% macro-F1. Using CLIP embeddings with XGBoost provides a strong alternative. In contrast, zero-shot CLIP and direct vision-language classification perform substantially worse, highlighting the limits of general-purpose models in this domain. Beyond overall performance, the analysis reveals which categories are visually separable and where errors reflect genuine semantic overlap, suggesting that some limitations arise from the taxonomy itself. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.33449 — 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 2026-10-07T22:14:28.720Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).