Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baró, A., Chen, J., Fornés, A., Megyesi, B.: Towards a generic unsupervised method for transcription of encoded manuscripts. In: DATeCH, pp. 73–78 (2019)
Ezra, D.S.B., Brown-DeVost, B., Dershowitz, N., Pechorin, A., Kiessling, B.: Transcription alignment for highly fragmentary historical manuscripts: the dead sea scrolls. In: ICFHR, pp. 361–366 (2020)
Fischer, A., Frinken, V., Fornés, A., Bunke, H.: Transcription alignment of Latin manuscripts using hidden Markov models. In: HIP, pp. 29–36 (2011)
Kang, L., Toledo, J.I., Riba, P., Villegas, M., Fornés, A., Rusiñol, M.: Convolve, attend and spell: an attention-based sequence-to-sequence model for handwritten word recognition. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 459–472. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_32
Kassis, M., Nassour, J., El-Sana, J.: Alignment of historical handwritten manuscripts using Siamese neural network. In: ICDAR, vol. 1, pp. 293–298 (2017)
Megyesi, B., et al.: Decryption of historical manuscripts: the decrypt project. Cryptologia 44(6), 545–559 (2020)
Riba, P., Fornés, A., Lladós, J.: Towards the alignment of handwritten music scores. In: GREC, pp. 103–116 (2015)
Romero-Gómez, V., Toselli, A.H., Bosch, V., Sánchez, J.A., Vidal, E.: Automatic alignment of handwritten images and transcripts for training handwritten text recognition systems. In: DAS, pp. 328–333 (2018)
Souibgui, M.A., Fornés, A., Kessentini, Y., Tudor, C.: A few-shot learning approach for historical ciphered manuscript recognition. In: ICPR, pp. 5413–5420 (2021)
Acknowledgement
This work has been supported by the Swedish Research Council, grant 2018-06074, DECRYPT – Decryption of Historical Manuscripts, the Spanish project RTI2018-095645-B-C21 and the CERCA Program / Generalitat de Catalunya.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Torras, P., Souibgui, M.A., Chen, J., Fornés, A. (2021). A Transcription Is All You Need: Learning to Align Through Attention. In: Barney Smith, E.H., Pal, U. (eds) Document Analysis and Recognition – ICDAR 2021 Workshops. ICDAR 2021. Lecture Notes in Computer Science(), vol 12916. Springer, Cham. https://doi.org/10.1007/978-3-030-86198-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-86198-8_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86197-1
Online ISBN: 978-3-030-86198-8
eBook Packages: Computer ScienceComputer Science (R0)
