Deep Learning-Based Approach for Old Handwritten Music Symbol Recognition
How to Cite?
Savitri Apparo Nawade, Mallikarjun Hangarge, Shivanand S Rumma, "Deep Learning-Based Approach for Old Handwritten Music Symbol Recognition," International Journal of Engineering Trends and Technology, vol. 69, no. 7, pp. 208-214, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I7P228
The advanced development in information and technology created a growing interest in optical music recognition for easy storage, access, and retrieval in digital form. By using OMR, we can transcribe music sheets into a machine-readable format. This facilitates the users to play, edit or compose the music. The handwritten music symbol recognition becomes more difficult as compared to print due to various issues such as a change in shape, distortion, etc. In this paper, the performance of deep learning-based method or old handwritten music symbol recognition was investigated by applying the MobileNetV2 architecture. In this stud, two approaches are presented. The first approach deals with the pure deep learning method, and in the second approach, the softmax layer is replaced with the traditional classifiers, namely-nearest neighbor classifier, support vector machine, and random forest classifier. Encouraging results were achieved on a publically available data set of old handwritten music symbols.
Convolutional Neural Networks, Handwritten Music Symbol Recognition, Deep Learning, Support Vector Machine, K-Nearest Neighbour Classifier, Random Forest Classifier.
 Ooi, Joyce Boon Ee, and Alan WC Tan., Music symbol recognition., (2011), 1-4.
 Na, I.S., Kim, S.H. Music symbol recognition by a LAG-based combination model. Multimedia Tools Applications 76(2017), 25563– 25579.
 A. Fornés, J. Lladós, G. Sanchez., Old Handwritten Musical Symbol Classification by a Dynamic Time Warping Based Method, in Graphics Recognition: Recent Advances and New Opportunities, Lecture Notes in Computer Science, (Eds. Liu, W. and Lladós, J. and Ogier, J.M.) 5046(2008), 51-60, Springer-Verlag Berlin, Heidelberg.
 Baró, Arnau, Pau Riba, Jorge Calvo-Zaragoza, and Alicia Fornés., From optical music recognition to handwritten music recognition: A baseline." Pattern Recognition Letters 123(2019), 1-8.
 A. Rebelo , G. Capela , J.S. Cardoso ,Optical recognition of music symbols: a com- parative study, International Journal of Document Analysis and Recognition. 13(1) (2010), 19–31
 Pacha, Alexander, Jorge Calvo-Zaragoza, and Jan Hajic Jr., Learning Notation Graph Construction for Full-Pipeline Optical Music Recognition, In ISMIR, (2019) 75-82.
 Calvo-Zaragoza, Jorge, Antonio-Javier Gallego, and Antonio Pertusa., Recognition of handwritten music symbols with convolutional neural codes., In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 1(2017),691-696. IEEE.
 Nawade, Savitri Apparao, Mallikarjun Hangarge, Chitra Dhawale, Mamun Bin Ibne Reaz, Rajmohan Pardeshi, and Norhana Arsad., Old handwritten music symbol recognition using directional multiresolution spatial features, In 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE), (2018),1-4. IEEE.
 Nawade, S.A., Rumma, S., Pardeshi, R. and Hangarge, M., Old Handwritten Music Symbol Recognition Using Radon and Discrete Wavelet Transform. In Advances in Artificial Intelligence and Data Engineering (2021),1165-1171. Springer, Singapore.
 Huang, Zhiqing, Xiang Jia, and Yifan Guo., State-of-the-art model for music object recognition with deep learning., Applied Sciences 9(13)(2019), 2645.
 Rashad, Marwa, and Noura A. Semary., Isolated printed Arabic character recognition using KNN and random forest tree classifiers., In International Conference on Advanced Machine Learning Technologies and Applications, (2014),11-17. Springer, Cham.
 Briman, L.: Random Forests. Machine Learning 45(1)(2001), 5–32.
 Saunders, Craig, Mark O. Stitson, Jason Weston, Leon Bottou, and A. Smola., Support vector machine-reference manual., (1998).
 Liao, Yihua, and V. Rao Vemuri., Use of k-nearest neighbor classifier for intrusion detection., Computers & security 21(5) (2002), 439-448.
 MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H, arXiv:1704.04861, (2017).
 MobileNetV2: Inverted Residuals and Linear Bottlenecks, Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. arXiv preprint. arXiv:1801.04381, (2018).
 Vapnik, Vladimir N., An overview of statistical learning theory, IEEE transactions on neural networks 10(5)(1999) 988-999.
 Isolated Old Handwritten Music Symbol Dataset,http://www.cvc.uab.es/people/afornes/datasets/datasets.html
 Malakar, S., Ghosh, M., Chaterjee, A. et al. Offline music symbol recognition using Daisy feature and quantum Grey wolf optimization based feature selection. Multimedia Tools Applications 79(2020),32011–32036.
 S. Chanda, D. Das, U. Pal and F. Kimura., Offline Hand-Written Musical Symbol Recognition, 2014 14th International Conference on Frontiers in Handwriting Recognition, (2014), 405-410.
 Jorge Calvo-Zaragoza, Jan Haji? Jr., and Alexander Pacha. 2020. Understanding Optical Music Recognition. ACM Comput. Surv. 53, 4, Article 77 (September 2020), 35 pages. DOI:https://doi.org/10.1145/3397499
 Novotný, J. and J. Pokorný., Introduction to Optical Music Recognition: Overview and Practical Challenges, DATESO (2015).
 S.Sunitha, Dr.S.S. Sujatha., Combined Feature Learning And CNN For Polyp Detection In Wireless Capsule Endoscopy Images" International Journal of Engineering Trends and Technology 69.6(2021):206-215.
 Sunil Pandey, Naresh Kumar Nagwani, Shrish Verma., Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks, International Journal of Engineering Trends and Technology 69.6(2021):216-224.