Detecting and Deciphering Damaged Medieval Armenian Inscriptions Using YOLO and Vision Transformers - Inria - Institut national de recherche en sciences et technologies du numérique
Chapitre D'ouvrage Année : 2024

Detecting and Deciphering Damaged Medieval Armenian Inscriptions Using YOLO and Vision Transformers

Chahan Vidal-Gorène
Aliénor Decours-Perez
  • Fonction : Auteur

Résumé

This paper investigates the development and assessment of a methodology for the automatic detection and interpretation of damaged medieval Armenian inscriptions and graffiti. The research utilizes a newly compiled dataset of 150 images that include a variety of inscriptions, mosaics, and graffiti. These images are sourced from general archaeological site views and vary in quality and type, including drone and archival photos, to replicate real-world database challenges. The results highlight the efficiency of a two-step detection and classification pipeline. The detection phase employs a YOLO v8 model to identify the location and content of inscriptions, achieving an average Precision and Recall of 0.91 and 0.88, respectively. The classification phase uses a Vision Transformer (ViT) to identify similar characters, which outperforms classic CNN-based Siamese networks to handle such a complexity and variation. This approach demonstrates potential for analyzing under-resourced and damaged corpora, thus facilitating the study of deteriorated inscriptions in a variety of contexts.
Fichier principal
Vignette du fichier
ICDAR2024_ArmenianInscriptions.pdf (14.52 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04722397 , version 1 (05-10-2024)

Licence

Identifiants

Citer

Chahan Vidal-Gorène, Aliénor Decours-Perez. Detecting and Deciphering Damaged Medieval Armenian Inscriptions Using YOLO and Vision Transformers. Document Analysis and Recognition – ICDAR 2024 Workshops, 14936, Springer Nature Switzerland, pp.22-36, 2024, Lecture Notes in Computer Science, ⟨10.1007/978-3-031-70642-4_2⟩. ⟨hal-04722397⟩

Collections

PSL ENC CJM
0 Consultations
0 Téléchargements

Altmetric

Partager

More