Abstract
In this paper, we propose a data-efficient holistic method for layout analysis in the context of Optical Music Recognition (OMR). Our approach can be trained by just providing the number of staves present in the document collection at issue (weak label), thereby making it practical for real use cases where other fine-grained annotations are expensive. We consider a Convolutional Recurrent Neural Network trained with the Connectionist Temporal Classification loss function, which must retrieve a pretext sequence that encodes the number of staves per page. As a by-product, the model learns to relate every image row according to the presence or not of a staff. We demonstrate that our approach achieves performances close to the full supervised scenario on two OMR benchmarks, according to the eventual performance of the full transcription pipeline. We believe that our work will be useful for researchers working on music score recognition, and will open up new avenues for research in this field.
This paper is part of the I+D+i project PID2020-118447RA-I00 (MultiScore), funded by MCIN/AEI/10.13039/501100011033.
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
Notes
- 1.
Even in the case of handwritten sources, the staff lines are printed or drawn with a ruling pen.
- 2.
The edit-distance function is implemented as the Levenshtein distance.
References
Alberti, M., Bouillon, M., Ingold, R., Liwicki, M.: Open evaluation tool for layout analysis of document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 04, pp. 43–47 (2017)
Bosch, V., Calvo-Zaragoza, J., Toselli, A.H., Vidal-Ruiz, E.: Sheet music statistical layout analysis. In: 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016, Shenzhen, China, 23–26 October 2016, pp. 313–8 (2016)
Calvo-Zaragoza Jr., J., J.H., Pacha, A.: Understanding optical music recognition. ACM Comput. Surv. 53(4), 77:1–77:35 (2021)
Calvo-Zaragoza, J., Toselli, A.H., Vidal, E.: Handwritten music recognition for mensural notation with convolutional recurrent neural networks. Pattern Recogn. Lett. 128, 115–121 (2019)
Calvo-Zaragoza, J., Toselli, A.H., Vidal, E.: Handwritten music recognition for mensural notation: Formulation, data and baseline results. In: 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, Kyoto, Japan, 9–15 November 2017, pp. 1081–1086 (2017)
Castellanos, F.J., Calvo-Zaragoza, J., Inesta, J.M.: A neural approach for full-page optical music recognition of mensural documents. In: ISMIR, pp. 558–565 (2020)
Castellanos, F.J., Gallego, A.J., Calvo-Zaragoza, J., Fujinaga, I.: Domain adaptation for staff-region retrieval of music score images. Int. J. Doc. Anal. Recognit. (IJDAR) 1–12 (2022)
Castellanos, F.J., Garrido-Munoz, C., Ríos-Vila, A., Calvo-Zaragoza, J.: Region-based layout analysis of music score images. Expert Syst. Appl. 209, 118211 (2022)
Graves, A.: Supervised sequence labelling with recurrent neural networks. Ph.D. thesis, Technical University Munich (2008)
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. ACM, New York (2006)
Parada-Cabaleiro, E., Batliner, A., Schuller, B.W.: A diplomatic edition of il lauro secco: Ground truth for OMR of white mensural notation. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019, Delft, The Netherlands, 4–8 November 2019, pp. 557–564 (2019)
Quirós, L., Toselli, A.H., Vidal, E.: Multi-task layout analysis of handwritten musical scores. In: Morales, A., Fierrez, J., Sánchez, J.S., Ribeiro, B. (eds.) IbPRIA 2019. LNCS, vol. 11868, pp. 123–134. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-31321-0_11
Waloschek, S., Hadjakos, A., Pacha, A.: Identification and cross-document alignment of measures in music score images. In: 20th International Society for Music Information Retrieval Conference, pp. 137–143 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ayllon, E., Castellanos, F.J., Calvo-Zaragoza, J. (2023). A Weakly-Supervised Approach for Layout Analysis in Music Score Images. In: Pertusa, A., Gallego, A.J., Sánchez, J.A., Domingues, I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2023. Lecture Notes in Computer Science, vol 14062. Springer, Cham. https://doi.org/10.1007/978-3-031-36616-1_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-36616-1_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36615-4
Online ISBN: 978-3-031-36616-1
eBook Packages: Computer ScienceComputer Science (R0)
