Research on Handwritten Music Score Recognition Based on Adversarial Domain Adaptive Transfer Learning_Vol. 4 No. 2 (JIKE 2026)_Journal of Intelligence and Knowledge Engineering (ISSN: 2959-0620)

Home > Journal of Intelligence and Knowledge Engineering (ISSN: 2959-0620) > Vol. 4 No. 2 (JIKE 2026) >

Research on Handwritten Music Score Recognition Based on Adversarial Domain Adaptive Transfer Learning

Download PDF

DOI: https://doi.org/10.62517/jike.202604202

Author(s)

Yangyu Gao

Affiliation(s)

Product Design and Manufacture, University of Nottingham Ningbo China, Ningbo, China

Abstract

Based on the PrIMuS dataset, this paper investigates handwritten music score recognition via the integration of adversarial domain adaptation and transfer learning, builds the end-to-end recognition model with TensorFlow, completes image preprocessing via OpenCV, develops the backend system with Flask, and verifies the high efficiency, stability and superior recognition performance of the whole scheme through systematic performance evaluation.

Keywords

Handwritten Music Score Recognition (HMSR); Adversarial Domain Adaptation (ADA); Transfer Learning (TL); PrIMuS Dataset; End-to-End Recognition System

References

[1] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[J]. Advances in neural information processing systems, 2014, 27. [2] S. J. Pan and Q. Yang, "A Survey on Transfer Learning," in IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct. 2010. [3] Aslam F A, Mohammed H N, Lokhande P S. Efficient Way Of Web Development Using Python And Flask[J]. International Journal of Advanced Research in Computer Science, 2015, 6(2). [4] Abadi M, TensorFlow A A B P. Large-scale machine learning on heterogeneous distributed systems[C]//Proceedings of the 12th USENIX symposium on operating systems design and implementation (OSDI’16)(Savannah, GA, USA. 2016: 265-283. [5] Bradski G. The opencv library[J]. Dr. Dobb's Journal: Software Tools for the Professional Programmer, 2000, 25(11): 120-123. [6] Mayer J, Pecina P, Hajič Jr J. Smashcima: Full-Page Handwritten Music Document Synthesizer[C]//Proceedings of the 12th International Conference on Digital Libraries for Musicology. 2025: 119-123. [7] J. Calvo-Zaragoza, A. H. Toselli and E. Vidal, "Handwritten Music Recognition for Mensural Notation: Formulation, Data and Baseline Results," 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017, pp. 1081-1086. [8] Oliva-Bulpitt S B, Martinez-Esteso J P, Galan-Cuenca A, et al. Enhancing music score analysis with Monte Carlo dropout: a probabilistic approach to staff-region detection[J]. International Journal on Document Analysis and Recognition (IJDAR), 2025: 1-16.https://doi.org/10.1007/s10032-025-00541-x. [9] Asbert G, Torras P, Kang L, et al. GAN-based Content-Conditioned Generation of Handwritten Musical Symbols[J]. arXiv preprint arXiv:2510.17869, 2025. [10] J. Calvo-Zaragoza, A. H. Toselli and E. Vidal, "Early Handwritten Music Recognition with Hidden Markov Models," 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China, 2016, pp. 319-324. [11] Mundada G, Vishe Y, Namburi A, et al. WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning[C]//Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025: 16858-16874. [12] Wu J, Guo W. Autoregressive ConvNeXt-Transformer Fusion Framework for Polyphonic Optical Music Recognition with Focal Loss Optimization[J]. Acoustical Science and Technology, 2025: e25. 60,doi:https://doi.org/10.1250/ast.e25.60. [13] Liu Y, Zou Y. Application of artificial intelligence based on pattern recognition in music entertainment environment and automatic music recognition[J]. Entertainment Computing, 2025, 52: 100848. [14] Huang Q, Zhu J, Xian Y, et al. Music score copyright protection based on mixed low-order quaternion Franklin moments[J]. PLoS One, 2025, 20(8): e0323447. [15] Cavez V, Letondal C, Appert C, et al. EuterPen: Unleashing Creative Expression in Music Score Writing[C]//Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 2025: 1-16. [16] Caftanatov O, Demidova V, Verlan T. An Approach to Recognizing and Digitizing Old Handwritten Documents with Mathematical Heterogeneous Content in Cyrillic script[J]. Computer Science Journal of Moldova, 2025, 97(1): 54-67.