Sirvi Autor "Heil, Raphaela" järgi

Nüüd näidatakse 1 - 3 3

listelement.badge.access-status Avatud juurdepääs ,
Decipherment of Historical Manuscripts with Unknown or Rare Writings: The DESCRYPT Project
(Tartu University Library, 2025) Megyesi, Beáta; Fornés, Alicia; Héder, Mihály; Heil, Raphaela; Kopal, Nils; Láng, Benedek; Rattenborg, Rune; Waldispühl, Michelle; Antal, Eugen; Marák, Pavol
We present a newly funded research program, DESCRYPT, aimed at deciphering and analyzing historical texts with rare or unknown scripts. The project leverages advancements in computational linguistics, artificial intelligence (AI), and image processing, alongside traditional philological methods, to develop innovative tools for transcription, recognition, and interpretation of historical writings with rare/unknown scripts, including ciphertexts. By integrating interdisciplinary expertise, DESCRYPT addresses the challenges posed by complex and undeciphered texts, preserving and unlocking the secrets of our shared cultural heritage.
listelement.badge.access-status Avatud juurdepääs ,
Establishing a Document Layout Analysis Baseline for Historical Cipher Keys
(Tartu University Library, 2026-06-22) Heil, Raphaela; Fornés, Alicia; Láng, Benedek; Megyesi, Beáta; Desenclos, Camille; Pierrot, Cécile
Historical cipher keys encode mappings between plaintext elements and cipher symbols and are characterized by complex, heterogeneous handwritten layouts. This paper establishes a baseline for document layout analysis (DLA) of historical cipher keys using a newly annotated dataset of 350 images from European archives dating from ca. 1300 to 1850 CE. We evaluate four YOLO-based architectures under three conditions: training from scratch, cross-domain transfer from models pre-trained on DocLayNet and CATMuS in a class-agnostic setting, and fine-tuning of these pre-trained models on cipher key data. Results show that training from scratch is limited by data scarcity and unstable convergence, while direct transfer across DLA domains performs poorly. In contrast, fine-tuning consistently improves performance across all architectures, demonstrating the feasibility of adapting existing DLA models to cipher keys and supporting downstream tasks such as key extraction and comparative cryptographic analysis.
listelement.badge.access-status Avatud juurdepääs ,
Learning to Decipher from Pixels—A Case Study of Copiale
(Tartu University Library, 2026-06-22) Kang, Lei; Gregorio, Giuseppe De; Heil, Raphaela; Fornés, Alicia; Megyesi, Beáta; Desenclos, Camille; Pierrot, Cécile
Historical encrypted manuscripts require both paleographic interpretation of cipher symbols and cryptanalytic recovery of plaintext. Most existing computational workflows rely on a transcription-first paradigm, in which handwritten symbols are transcribed prior to decipherment. This intermediate step is labor-intensive, error-prone, and not always aligned with the goal of direct plaintext recovery. We propose an end-to-end, transcription-free approach that directly maps handwritten cipher images to plaintext. Using the Copiale cipher as a case study, we introduce the first text-line-level dataset pairing cipher images with German plaintext. We show that pretraining on generic handwriting data followed by cipher-specific fine-tuning substantially improves decipherment accuracy. Our results demonstrate that transcription-free image-to- plaintext decipherment is both feasible and effective for historical substitution ciphers, offering a simplified and scalable alternative to traditional pipelines.