EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing music score analysis with Monte Carlo dropout: a probabilistic approach to staff-region detection

Samuel B. Oliva-Bulpitt, Juan P. Martinez-Esteso, Alejandro Galan-Cuenca, Francisco J. Castellanos, Antonio Javier Gallego

International Journal on Document Analysis and Recognition (IJDAR) · 2025-09 · 28 (3) · 441-456

DOI: 10.1007/s10032-025-00541-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal on Document Analysis and Recognition (IJDAR), online erschienen am 20.06.2025. Verfasst von Samuel B. Oliva-Bulpitt und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Generalitat Valenciana, Universidad de Alicante.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Layout Analysis (LA) is a critical process for detecting and isolating different components within a scanned document, allowing for more straightforward and precise processing of each part independently. In Optical Music Recognition (OMR), LA is essential for identifying and extracting music staves, which enables effective music notation recognition and processing. While the literature includes several studies exploring methods for staff retrieval, there remains room for improvement in terms of robustness and accuracy. In this work, we introduce a methodology that integrates Monte Carlo Dropout (MCD) into a neural network model in order to improve reliability in staff retrieval from scanned sheet music. Our approach leverages multiple non-deterministic predictions using standard dropout layers during inference and aggregates them through pixel-level combination policies. We extend the MCD technique, originally designed for classification and regression tasks using averaged predictions, to the LA task and introduce new combination strategies: maximum and voting criteria. Experiments on three diverse music score corpora, including printed and handwritten documents, demonstrated the effectiveness of our approach. The averaging and voting (with 25% and 50% of votes) criteria reduced the relative error by 63.6% compared to the baseline and achieved a 32.1% improvement over state-of-the-art methods. Our methodology notably enhanced detection accuracy without requiring modifications to the neural architecture, especially at the edges of staves, where conventional models tend to show higher error rates.

Förderung

  • Generalitat Valenciana
  • Universidad de Alicante

Zitieren

APA

Oliva-Bulpitt, S. B., Martinez-Esteso, J. P., Galan-Cuenca, A., Castellanos, F. J., & Gallego, A. J. (2025). Enhancing music score analysis with Monte Carlo dropout: a probabilistic approach to staff-region detection. International Journal on Document Analysis and Recognition (IJDAR), 28(3), 441-456. https://doi.org/10.1007/s10032-025-00541-x

Vancouver

Oliva-Bulpitt SB, Martinez-Esteso JP, Galan-Cuenca A, Castellanos FJ, Gallego AJ. Enhancing music score analysis with Monte Carlo dropout: a probabilistic approach to staff-region detection. International Journal on Document Analysis and Recognition (IJDAR). 2025;28(3):441-456. doi:10.1007/s10032-025-00541-x

BibTeX
@article{OlivaBulpitt2025,
  author = {Oliva-Bulpitt, Samuel B. and Martinez-Esteso, Juan P. and Galan-Cuenca, Alejandro and Castellanos, Francisco J. and Gallego, Antonio Javier},
  title = {Enhancing music score analysis with Monte Carlo dropout: a probabilistic approach to staff-region detection},
  journal = {International Journal on Document Analysis and Recognition (IJDAR)},
  year = {2025},
  volume = {28},
  number = {3},
  pages = {441--456},
  doi = {10.1007/s10032-025-00541-x}
}
Kostenlos starten →