Skip to main content

Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images

  • Conference paper
  • First Online:
Document Analysis and Recognition – ICDAR 2023 Workshops (ICDAR 2023)


Developing arbitrary symbol recognition systems is a challenging endeavour. Even using content-agnostic architectures such as few-shot models, performance can be substantially improved by providing a number of well-annotated examples into training. In some contexts, transcripts of the symbols are available without any position information associated to them, which enables using line-level recognition architectures. A way of providing this position information to detection-based architectures is finding systems that can align the input symbols with the transcription. In this paper we discuss some symbol alignment techniques that are suitable for low-data scenarios and provide an insight on their perceived strengths and weaknesses. In particular, we study the usage of Connectionist Temporal Classification models, Attention-Based Sequence to Sequence models and we compare them with the results obtained on a few-shot recognition system.

Supported by the DECRYPT Project (grant 2018-0607).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 74.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others


  1. Aldarrab, N., Knight, K., Megyesi, B.: The Cipher (2018).

  2. Baró, A., Chen, J., Fornés, A., Megyesi, B.: Towards a generic unsupervised method for transcription of encoded manuscripts. In: Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage, DATeCH2019, pp. 73–78. Association for Computing Machinery, New York (2019).

  3. De Gregorio, G., Capriolo, G., Marcelli, A.: End-to-end transcript alignment of 17th century manuscripts: the case of Moccia code. J. Imaging 9(1), 17 (2023).,

  4. De Gregorio, G., Citro, I., Marcelli, A.: Transcript alignment for historical handwritten documents: the MiM algorithm. In: Carmona-Duarte, C., Diaz, M., Ferrer, M.A., Morales, A. (eds.) IGS 2022. LNCS, vol. 13424, pp. 45–60. Springer, Cham (2022).

    Chapter  Google Scholar 

  5. Feng, S., Manmatha, R.: A hierarchical, HMM-based automatic evaluation of OCR accuracy for a digital library of books. In: Proceedings of the 6th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL 2006, pp. 109–118. Association for Computing Machinery, New York (2006).

  6. Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd international conference on Machine learning, ICML 2006, pp. 369–376. Association for Computing Machinery, New York (2006).

  7. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)

    Google Scholar 

  8. Indermühle, E., Liwicki, M., Bunke, H.: Combining alignment results for historical handwritten document analysis. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 1186–1190 (2009). iSSN 2379-2140

  9. Kirillov, A., et al.: Segment anything (2023)., arXiv:2304.02643 [cs]

  10. Knight, K., Megyesi, B., Schaefer, C.: The Copiale cipher. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 2–9. Association for Computational Linguistics, Portland (2011).

  11. Kornfield, E., Manmatha, R., Allan, J.: Text alignment with handwritten documents. In: 2004 Proceedings of First International Workshop on Document Image Analysis for Libraries, pp. 195–209 (2004).

  12. Levenshtein, V.I., et al.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet Physics Doklady, vol. 10, pp. 707–710. Soviet Union (1966)

    Google Scholar 

  13. Liu, H., Jin, S., Zhang, C.: Connectionist temporal classification with maximum entropy regularization. In: Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018).

  14. Megyesi, B., et al.: Decryption of historical manuscripts: the decrypt project. Cryptologia 44(6), 545–559 (2020)

    Article  Google Scholar 

  15. Müller, M.: Dynamic time warping. In: Müller, M. (ed.) Information Retrieval for Music and Motion, pp. 69–84. Springer, Heidelberg (2007).

    Chapter  Google Scholar 

  16. Souibgui, M.A., Fornés, A., Kessentini, Y., Megyesi, B.: Few shots are all you need: a progressive learning approach for low resource handwritten text recognition. Pattern Recognit. Lett. 160, 43–49 (2022).,

  17. Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014).

  18. Torras, P., Souibgui, M.A., Chen, J., Fornés, A.: A transcription is all you need: learning to align through attention. In: Barney Smith, E.H., Pal, U. (eds.) ICDAR 2021. LNCS, vol. 12916, pp. 141–146. Springer, Cham (2021).

    Chapter  Google Scholar 

  19. Toselli, A.H., Romero, V., Vidal, E.: Viterbi based alignment between text images and their transcripts. In: Proceedings of the Workshop on Language Technology for Cultural Heritage Data (LaTeCH 2007), pp. 9–16. Association for Computational Linguistics, Prague (2007).

  20. Yalniz, I.Z., Manmatha, R.: A fast alignment scheme for automatic OCR evaluation of books. In: 2011 International Conference on Document Analysis and Recognition, pp. 754–758 (2011). iSSN 2379-2140

  21. Zenkel, T., et al.: Comparison of decoding strategies for CTC acoustic models (2017)., arXiv:1708.04469 [cs]

  22. Zeyer, A., Schlüter, R., Ney, H.: Why does CTC result in peaky behavior? (2021)., arXiv:2105.14849 [cs, eess, math, stat]

Download references


This work has been partially supported by the Swedish Research Council (grant 2018-06074, DECRYPT), the Spanish projects PID2021-126808OB-I00 (GRAIL) and CNS2022-135947 (DOLORES), as well as the AGAUR Joan Oró FI grant 2023 FI-1-00324. The authors acknowledge the support of the Generalitat de Catalunya CERCA Program to CVC’s general activities.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Pau Torras .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Torras, P., Souibgui, M.A., Chen, J., Biswas, S., Fornés, A. (2023). Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images. In: Coustaty, M., Fornés, A. (eds) Document Analysis and Recognition – ICDAR 2023 Workshops. ICDAR 2023. Lecture Notes in Computer Science, vol 14193. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-41497-8

  • Online ISBN: 978-3-031-41498-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics