Music Symbol Detection with Faster R-CNN Using Synthetic Annotations

Abstract : Accurately detecting music symbols in images of historical, complex, dense orchestral or piano printed scores can be challenging due to old printing techniques or time degradations. Because segmentation problems can vary widely, a data driven approach like the use of deep learning detectors is needed. However, the production of detection annotations (symbol bounding boxes + classes) for such systems is costly and time consuming. We propose to train such model with synthetic data and annotations produced by a music typesetting program. We analyze which classes are relevant to the detection task and present a first selection of music score typesetting files that will be used for training. To evaluate our model, we plan to compute quantitative results on a synthetic test set and provide qualitative results on a few manually annotated historical music scores.
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01972434
Contributor : Kwon-Young Choi <>
Submitted on : Monday, January 7, 2019 - 4:51:37 PM
Last modification on : Thursday, February 7, 2019 - 3:40:01 PM
Long-term archiving on : Monday, April 8, 2019 - 4:07:29 PM

File

830dba4849af0cd56c0abd21eb9fa7...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01972434, version 1

Citation

Kwon-Young Choi, Bertrand Coüasnon, Yann Ricquebourg, Richard Zanibbi. Music Symbol Detection with Faster R-CNN Using Synthetic Annotations. 1st International Workshop on Reading Music Systems, Sep 2018, Paris, France. ⟨hal-01972434⟩

Share

Metrics

Record views

126

Files downloads

51