Arnau Baro author Jialuo Chen author Alicia Fornes author Beata Megyesi author 2019 Historical ciphers, a special type of manuscripts, contain encrypted information, important for the interpretation of our history. The first step towards decipherment is to transcribe the images, either manually or by automatic image processing techniques. Despite the improvements in handwritten text recognition (HTR) thanks to deep learning methodologies, the need of labelled data to train is an important limitation. Given that ciphers often use symbol sets across various alphabets and unique symbols without any transcription scheme available, these supervised HTR techniques are not suitable to transcribe ciphers. In this paper we propose an un-supervised method for transcribing encrypted manuscripts based on clustering and label propagation, which has been successfully applied to community detection in networks. We analyze the performance on ciphers with various symbol sets, and discuss the advantages and drawbacks compared to supervised HTR methods. A. Baró J. Chen A. Fornés B. Megyesi. DAG; 600.097; 600.140; 600.121 exported from refbase (http://refbase.cvc.uab.es/show.php?record=3276), last updated on Tue, 24 Nov 2020 12:27:18 +0100 text http://refbase.cvc.uab.es/files/BCF2019.pdf 10.1145/3322905.3322920 Admin @ si @ BCF2019 DATeCH 2019 conference publication 73 78