Handwritten Music Object Detection: Open Issues and Baseline Results

  title={Handwritten Music Object Detection: Open Issues and Baseline Results},
  author={Alexander Pacha and Kwon-Young Choi and Bertrand Co{\"u}asnon and Yann Ricquebourg and Richard Zanibbi and Horst M. Eidenberger},
  journal={2018 13th IAPR International Workshop on Document Analysis Systems (DAS)},
Optical Music Recognition (OMR) is the challenge of understanding the content of musical scores. Accurate detection of individual music objects is a critical step in processing musical documents because a failure at this stage corrupts any further processing. So far, all proposed methods were either limited to typeset music scores or were built to detect only a subset of the available classes of music symbols. In this work, we propose an end-to-end trainable object detector for music symbols… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • By training deep convolutional neural networks on the recently released MUSCIMA++ dataset which has symbol-level annotations, we show that a machine learning approach can be used to accurately detect music objects with a mean average precision of over 80%.


Publications referenced by this paper.
Showing 1-10 of 25 references

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015
View 9 Excerpts
Highly Influenced

Focal Loss for Dense Object Detection

IEEE transactions on pattern analysis and machine intelligence • 2018
View 1 Excerpt

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

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) • 2017
View 1 Excerpt

Hajič and P. Pecina, “The MUSCIMA++ dataset for handwritten optical music recognition.

J. j
Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, • 2017
View 2 Excerpts

Similar Papers

Loading similar papers…