2ⁿᵈ Exchange Meeting of SCOOP: International Network for Automated Text Recognition of Historical Sources

Session

Working Group 2

WG2

Sep 8, 2026, 9:00 AM

University of Vienna

16. From Handwriting Classification Errors to Paleographic Evidence: Graphic Compensation in Ancient Greek Documentary Hands

Asimina Paparrigopoulou (Democritus University of Thrace), Paraskevi Platanou (Athens University of Economics and Business, and Archimedes, Athena Research Center, Greece)

9/8/26, 9:00 AM

Handwriting classification is usually evaluated through predictive accuracy, yet the structure of its errors can also provide evidence about the visual organization of historical scripts. In this work, we analyze a ConvNeXt-V2 classifier for handwritten ancient Greek letterforms trained with lacuna-based fragmentation and dynamically learned supervised contrastive loss. Rather than treating...

17. Classification of Armenian manuscripts without OCR/HTR preprocessing

Tara Andrews (University of Vienna)

9/8/26, 9:30 AM

Armenian manuscripts are a particularly rich corpus when it comes to their premodern “metadata” - the addition of a colophon, usually naming the scribe and often giving the date as well as circumstantial information about the production of the manuscript, was a strong element of the copying tradition. Moreover, when it exists, this metadata is usually reproduced in the manuscript catalogue...

18. Beyond the Heatmap: What Faithful Explanations Can Do for Handwriting Identification

Serena Ammirati (Università degli Studi Roma Tre), Paolo Merialdo (Roma Tre University)

9/8/26, 10:00 AM

Explainable AI for handwriting identification has so far mostly stopped at the heatmap: pixel-level relevance maps that scholars can inspect but rarely act upon. This talk traces a path from diagnosis to action to discovery. We first present a validated, model-agnostic explainability framework for medieval handwriting classifiers, assessed for faithfulness, stability, and cross-model...

13. Classifying Squeezes Again: Initial Results from an ICDAR Contest

Aaron Hershkowitz (The Institute for Advanced Study)

9/8/26, 11:00 AM

At the first SCOOP meeting in June 2025 Aaron Hershkowitz and Nicholas Howe presented the results of their 2024-25 NEH-funded project to evaluate various approaches to automated text recognition. Two main text recognition approaches were explored: traditional sequential Optical Character Recognition (OCR), and Scene Text Detection. Out of the box OCR engines like Kraken were found not to...

14. Communities of Practice: Capturing the Aspect of Late Medieval Handwriting

Sebastian Sobecki (University of Toronto), Sam Grieggs (Indiana University of Pennsylvania)

9/8/26, 11:30 AM

Communities of Practice is funded by the Social Sciences and Humanities Research Council of Canada and explores how the multilingual urban bureaucracy of London — the world of Chaucer and his contemporaries — shaped late medieval literature. Bringing together linguistic, palaeographical, literary-historical, and computational methods, the project examines how networks of clerks employed in...

15. Script classification and alphabet identification

Giuseppe De Gregorio (Computer Vision Center - CVC - Barcelona)

9/8/26, 12:00 PM

Handwritten Text Recognition assumes what encrypted historical manuscripts withhold: a known script, and labelled examples of it. Two questions therefore come first. Which script family does this document belong to, and which symbols does it actually use? Both are still answered by hand, an expert-bound process that does not scale to collections of hundreds of manuscripts. This talk reports...