They're veGAN but they almost taste the same: generating simili-manuscripts with artificial intelligence - CAMPUS CONDORCET Access content directly
Conference Papers Year :

They're veGAN but they almost taste the same: generating simili-manuscripts with artificial intelligence

Chahan Vidal-Gorène
Jean-Baptiste Camps

Abstract

The aim of our research is to artificially generate fake historical manuscripts using generative adversarial networks, better known as GANs. At this stage, these experiments pursue two objectives: evaluating feasibility of generating realistic fake manuscripts under certain conditions of layout, script, or date, and creating artificial data for HTR training, as is done for printed materials with synthetic data. Ground truth creation is indeed a time consuming task, in particular for ancient languages for which we still lack specialists able to manually annotate documents. GAN appears as a relevant answer to this challenge, as they reach very convincing results in different scenarii. This short paper investigates the feasibility of the line-level approach for historical manuscripts.
Fichier principal
Vignette du fichier
DH_Graz_2023_Fake_Manuscripts_final.pdf (1.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
licence : CC BY SA - Attribution - ShareAlike

Dates and versions

hal-04086940 , version 1 (18-05-2023)

Licence

Attribution - ShareAlike

Identifiers

  • HAL Id : hal-04086940 , version 1

Cite

Chahan Vidal-Gorène, Jean-Baptiste Camps. They're veGAN but they almost taste the same: generating simili-manuscripts with artificial intelligence. Digital Humanities 2023: Collaboration as opportunity, Alliance of Digital Humanities Organisations, Jul 2023, Graz, Austria. ⟨hal-04086940⟩
43 View
26 Download

Share

Gmail Facebook Twitter LinkedIn More