García, GoioTorras, PauFornés, AliciaMegyesi, BeátaWaldispühl, MichelleMegyesi, Beáta2024-05-082024-05-0820241736-6305https://hdl.handle.net/10062/98471https://doi.org/10.58009/aere-perennius0096The automatic transcription of encrypted manuscripts is a challenge due to the different handwriting styles and the often invented symbol alphabets. Many transcription methods require annotated sources, including symbol locations. However, most existing transcriptions are provided at line or page level, making it necessary to find the bounding boxes of the transcribed symbols in the image, a process referred to as alignment. So, in this work, we develop several alignment methods, and discuss their performance on encrypted documents with various symbol sets.enAttribution-NonCommercial-NoDerivatives 4.0 InternationalEncrypted manuscriptsText-to-image alignmentTranscription alignmentDeep learningSequence learningArticle