Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Staff-line and Measure Detection using a Convolutional Neural Network for Handwritten Optical Music Recognition

손사보 악보의 광학음악인식을 위한 CNN 기반의 보표 및 마디 인식

  • Received : 2022.06.13
  • Accepted : 2022.06.28
  • Published : 2022.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the development of computer music notation programs, when drawing sheet music, it is often drawn using a computer. However, there are still many use of hand-written notations for educational purposes or to quickly draw sheet music such as listening and dictating. In previous studies, OMR focused on recognizing the printed music sheet made by music notation program. the result of handwritten OMR with camera is poor because different people have different writing methods, and lens distortion. In this study, as a pre-processing process for recognizing handwritten music sheet, we propose a method for recognizing a staff using linear regression and a method for recognizing a bar using CNN. F1 scores of staff recognition and barline detection are 99.09% and 95.48%, respectively. This methodologies are expected to contribute to improving the accuracy of handwriting.

Keywords

Acknowledgement

This research is supported by Ministry of Cultures, Sports and Tourism and Korea Creative Content Agency(Project Number: R2021050006)

References

  1. A. Pacha, K. -Y. Choi, B. Couasnon, Y. Ricquebourg, R. Zanibbi, and H. Eidenberger, "Handwritten Music Object Detection: Open Issues and Baseline Results," in Proceeding of 13th IAPR International Workshop on Document Analysis Systems, Vienna, Austria, pp. 163-168, 2018. DOI: 10.1109/DAS.2018.51.
  2. F. Alirezazadeh and M. R. Ahmadzadeh, "Effective staff line detection, restoration and removal approachfor different quality of scanned handwritten music sheets," Journal of Advanced Computer Science & Technology, vol. 3, no. 2, pp. 136-142, Jun. 2014. DOI: 10.14419/jacst.v3i2.3196.
  3. A. J. Gallego and J. Callvo-Zaragoza "Staff-line Removal with Selectional Auto-Encoders," Expert Systems with Applications, vol. 89, pp. 138-148, Dec. 2017. DOI:https://doi.org/10.1016/j.eswa.2017.07.002.
  4. F. J. Castellanos, J. Calvo-Zaragoza, G. Vigliensoni, and I. Fujinaga, "Document Analysis of Music Score Images with Selectional Auto-encoders," in Proceeding of the 19th International Society for Music Information Retrieval Conference, Paris, France, pp. 256-263, 2018. DOI:10.5281/zenodo.1492397.
  5. A. Fornes, A. Dutta, A. Gordo, and J. Llados, "CVC-MUSCIMA: A Ground-truth of Handwritten Music Score Images for Writer Identification and Staff Removal," International Journal on Document Analysis and Recognition, vol. 15, no. 3, pp. 243-251, Jun. 2012. DOI: 10.1007/s10032-011-0168-2.
  6. A. Baro, P. Riba, J. Calvo-Zaragoza, and A. Fornes. "From Optical Music Recognition to Handwritten Music Recognition: a Baseline," Pattern Recognition Letters, vol. 123, pp. 1-8, May. 2019. DOI: 10.1016/j.patrec.2019.02.029.
  7. J. Calvo-Zaragoza, A. Pertusa, and J. Oncina, "Staff-line detection and removal using a convolutional neural network," Machine Vision and Applications, vol. 28, pp. 665-674, May. 2017. DOI: 10.1007/s00138-017-0844-4.