Convolutional Neural Networks and Ensemble Methods to Identify Musical Elements in Optical Music Recognition
Keywords:
Optical Music Recognition, Convolutional Neural Network, Ensemble Learning MethodsAbstract
Optical Music Recognition (OMR) is an important tool to recognize a scanned page of music sheet automatically, which has been applied to preserving music scores. In this paper, we present a comparative study among a Convolutional Neural Network (CNN) architecture, named CREATES, and Ensemble Learning methods, such as Random Forest and XGBoost, to classify musical symbols. The initial results show that CREATES is promising in this task and it outperforms ensemble methods on the HOMUS dataset. However, CNN require more computing power.
Downloads
References
Bainbridge, D. and Bell, T. (2001). The challenge of optical music recognition. Computers and the Humanities, 35(2):95–121.
Barbosa, J. and Santos, E. (2021). Creates - convolutional neural network applied to identification of musical elements in omr. In Anais do XVIII Simposio Brasileiro de Computacao Musical, pages 221–224, Porto Alegre, RS, Brasil. SBC.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Bruce, P. and Bruce, A. (2017). Practical Statistics for Data Scientists. O’Reilly Media, Sebastopol, CA.
Calvo-Zaragoza, J., Jr, J. H., and Pacha, A. (2020). Understanding optical music recognition. ACM Computing Surveys (CSUR), 53(4):1–35.
Dalitz, C., Droettboom, M., Pranzas, B., and Fujinaga, I. (2008). A comparative study of staff removal algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(5):753–766.
de Paulo, A. M., Schiavoni, F. L., de Matos Laia, M. A., and Madeira, D. L. A. (2015). Copista-sistema de omr para a recuperação de acervo histórico musical. XV SBCM-Computer Music: Beyond the frontiers of signal processing and computational models.
dos Santos Cardoso, J., Capela, A., Rebelo, A., Guedes, C., and da Costa, J. P. (2009). Staff detection with stable paths. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(6):1134–1139.
Dumoulin, V. and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285.
Forn ́es, A., Llad ́os, J., and S ́anchez, G. (2005). Primitive segmentation in old handwritten music scores. In International Workshop on Graphics Recognition, pages 279–290. Springer.
Fujinaga, I. (2004). Staff detection and removal. In Visual Perception of Music Notation: On-Line and Off Line Recognition, pages 1–39. IGI Global.
Huang, Z., Jia, X., and Guo, Y. (2019). State-of-the-art model for music object recognition with deep learning. Applied Sciences, 9(13).
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. nature, 521(7553):436–444.
Rebelo, A., Capela, G., and Cardoso, J. S. (2010). Optical recognition of music symbols. International Journal on Document Analysis and Recognition (IJDAR), 13(1):19–31.
Rebelo, A. and Cardoso, J. S. (2013). Staff line detection and removal in the grayscale domain. In 2013 12th International Conference on Document Analysis and Recognition, pages 57–61. IEEE.
Rossant, F. and Bloch, I. (2006). Robust and adaptive omr system including fuzzy modeling, fusion of musical rules, and possible error detection. EURASIP Journal on Advances in Signal Processing, 2007(1):081541.
van der Wel, E. and Ullrich, K. (2017). Optical music recognition with convolutional sequence-to-sequence models. In Cunningham, S. J., Duan, Z., Hu, X., and Turnbull, D., editors, Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017, Suzhou, China, October 23-27, 2017, pages 731–737.
Wen, C., Rebelo, A., Zhang, J., and Cardoso, J. (2015). A new optical music recognition system based on combined neural network. Pattern Recognition Letters, 58:1–7.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Os Autores
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
