Details

Autor(en) / Beteiligte

• Torras, Pau
• Souibgui, Mohamed Ali
• Chen, Jialuo
• Fornés, Alicia

Titel

A Transcription Is All You Need: Learning to Align Through Attention

Ist Teil von

• Document Analysis and Recognition – ICDAR 2021 Workshops, p.141-146

Ort / Verlag

Cham: Springer International Publishing

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Historical ciphered manuscripts are a type of document where graphical symbols are used to encrypt their content instead of regular text. Nowadays, expert transcriptions can be found in libraries alongside the corresponding manuscript images. However, those transcriptions are not aligned, so these are barely usable for training deep learning-based recognition methods. To solve this issue, we propose a method to align each symbol in the transcript of an image with its visual representation by using an attention-based Sequence to Sequence (Seq2Seq) model. The core idea is that, by learning to recognise symbols sequence within a cipher line image, the model also identifies their position implicitly through an attention mechanism. Thus, the resulting symbol segmentation can be later used for training algorithms. The experimental evaluation shows that this method is promising, especially taking into account the small size of the cipher dataset.