Skip to Main content Skip to Navigation
Conference papers

Bootstrapping Samples of Accidentals in Dense Piano Scores for CNN-Based Detection

Abstract : State-of-the-art Optical Music Recognition system often fails to process dense and damaged music scores, where many symbols can present complex segmentation problems. We propose to resolve these segmentation problems by using a CNN-based detector trained with few manually annotated data. A data augmentation bootstrapping method is used to accurately train a deep learning model to do the localization and classification of an accidental symbol associated with a note head, or the note head if there is no accidental. Using 5-fold cross-validation, we obtain an average of 98.5% localization with an IoU score over 0.5 and a classification accuracy of 99.2%.
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01712213
Contributor : Kwon-Young Choi <>
Submitted on : Monday, February 19, 2018 - 11:42:04 AM
Last modification on : Friday, March 6, 2020 - 4:32:02 PM
Document(s) archivé(s) le : Monday, May 7, 2018 - 12:30:59 PM

File

GREC_2017_camera_ready.pdf
Files produced by the author(s)

Identifiers

Citation

Kwon-Young Choi, Bertrand Coüasnon, Yann Ricquebourg, Richard Zanibbi. Bootstrapping Samples of Accidentals in Dense Piano Scores for CNN-Based Detection. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Nov 2017, Kyoto, Japan. ⟨10.1109/ICDAR.2017.257⟩. ⟨hal-01712213⟩

Share

Metrics

Record views

375

Files downloads

244