TY  - CONF
AU  - Giacomo Magnifico
AU  - Beata Megyesi
AU  - Mohamed Ali Souibgui
AU  - Jialuo Chen
AU  - Alicia Fornes
A2  - HystoCrypt
PY  - 2022//
TI  - Lost in Transcription of Graphic Signs in Ciphers
BT  - International Conference on Historical Cryptology (HistoCrypt 2022)
SP  - 153
EP  - 158
KW  - transcription of ciphers
KW  - hand-written text recognition of symbols
KW  - graphic signs
N2  - Hand-written Text Recognition techniques with the aim to automatically identify and transcribe hand-written text have been applied to historical sources including ciphers. In this paper, we compare the performance of two machine learning architectures, an unsupervised method based on clustering and a deep learning method with few-shot learning. Both models are tested on seen and unseen data from historical ciphers with different symbol sets consisting of various types of graphic signs. We compare the models and highlight their differences in performance, with their advantages and shortcomings.
UR  - https://doi.org/10.3384/ecp188403
L1  - http://refbase.cvc.uab.es/files/MBS2022.pdf
N1  - DAG; 600.121; 600.162; 602.230; 600.140
ID  - Giacomo Magnifico2022
ER  -