%0 Conference Proceedings
%T Lost in Transcription of Graphic Signs in Ciphers
%A Giacomo Magnifico
%A Beata Megyesi
%A Mohamed Ali Souibgui
%A Jialuo Chen
%A Alicia Fornes
%B International Conference on Historical Cryptology (HistoCrypt 2022)
%D 2022
%F Giacomo Magnifico2022
%O DAG; 600.121; 600.162; 602.230; 600.140
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3731), last updated on Tue, 25 Apr 2023 16:06:43 +0200
%X 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.
%K transcription of ciphers
%K hand-written text recognition of symbols
%K graphic signs
%U https://doi.org/10.3384/ecp188403
%U http://refbase.cvc.uab.es/files/MBS2022.pdf
%P 153-158