Work

CLLG Ancient Greek Printed Edition Segmentation

Year: 2026

Type: article

Abstract: This model is trained on 800 pages of printed edition, with a vocabulary close to LADaS (Without P subcategories). The dataset is made of https://zenodo.org/records/22098097, with around different 70 books (from a dozen pages to 2 pages minimum per book).

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.24077352

Authors: Thibault Clérice, Karamolegkou, Antonia, Laurent, Maïna, Angleraud, Nicolas

Institution: Institut national de recherche en sciences et technologies du numérique

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7225624388

FWCI:

Cites:

Cited by:

Related to: