Metric Learning for Music Symbol Recognition

Rebelo, Ana; Tkaczuk, Jakub; Sousa, Ricardo J. Alves de; Cardoso, Jaime S.

doi:10.1109/icmla.2011.94

Cited by 9 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taubman et al [32] utilized statistical moments for note recognition. Rebelo et al [33] conduct a comparative evaluation of four recognition and classification methods. Among these methods, Support Vector Machine (SVM) and k-NN algorithms demonstrated better performance, while HMM and Neural Networks (NNs) did not exhibit remarkable classification results.…”

Section: B Note Recognitionmentioning

confidence: 99%

Deep Multilevel Cascade Residual Recurrent Framework (MCRR) for Sheet Music Recognition

Yu,

Chen

2024

IEEE Access

View full text Add to dashboard Cite

Sheet music recognition is a vital technology aimed at converting printed or handwritten musical scores into digital or machine-readable formats. The significance of this technology lies in making music compositions more accessible for editing, performance, learning, and sharing, thereby fostering music education, composition, and culture. It also provides a powerful tool for music analysis, research, and preservation. Our aim is to investigate a sheet music recognition method that offers a simple workflow, high recognition accuracy, and fast model convergence. Specifically, the proposed Deep Multilevel Cascade Residual Recurrent (MCRR) framework for sheet music recognition consists of the following components. Firstly, we introduce additive Gaussian white noise, additive Perlin noise, and elastic deformations such as rotation and stretching to simulate real-world noise in the sheet music images, thereby augmenting the dataset, enhancing model robustness, and mitigating overfitting. Secondly, in the feature extraction phase, we employ a residual Convolutional Neural Network (ConvNet) to address the issue of model degradation and use the multilevel cascade fusion technique to obtain comprehensive feature information, improving the model's feature extraction capability and reducing recognition errors. For note recognition, we use a variant of RNN (Recurrent Neural Network) called SRU (Simple Recurrent Unit), which transforms most computations into parallel processing, speeding up model convergence. Finally, we combine the Connectionist Temporal Classification (CTC) loss function with SRU to eliminate the requirement for strict alignment between data and labels, enabling note classification and recognition. Extensive ablation experiments and comparative analyses, including visual analysis, intuitive illustrations, and quantitative assessments, confirm the effectiveness of the proposed method, demonstrating its superiority over various state-of-the-art methods. The proposed method achieved promising results in both the PrIMus and Camera-PrIMuS datasets. Specifically, in the PrIMus dataset, the method obtained an SeER (Symbol Error Rate) of 1.4571% and a SyER (System Error Rate) of 0.3234%. Notably, it demonstrated high accuracy in pitch, type, and note recognition, scoring approximately 97% in pitch and type accuracy and around 94% in note accuracy. The training time per epoch was relatively low, recorded at 0.56 seconds. In the case of the Camera-PrIMuS dataset, the method achieved slightly lower but still competitive results. It exhibited an SeER of 5.1488% and a SyER of 1.0612%, with pitch and type accuracies around 90%, and note accuracy at approximately 88%. The training time per epoch was slightly higher at 1.93 seconds Furthermore, we compare our method with existing commercial software, namely Capella-scan, PhotoScore, and SmartScore. Among these, Capella-scan delivers the best performance but exhibits lower robustness compared to the proposed method.INDEX TERMS Sheet music recognition, deep learning, multile...

show abstract

Section: B Note Recognitionmentioning

confidence: 99%

Deep Multilevel Cascade Residual Recurrent Framework (MCRR) for Sheet Music Recognition

Yu,

Chen

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Finally, the chosen output representation of the music notation reconstruction step must be a good input for the next stage: encoding the information in the desired output format. There is a plethora of music encoding formats: from the text-based formats such as DARMS, 9 ** kern, 10 LilyPond, ABC, 11 over NIFF, 12 MIDI, 13 to XML-based formats MusicXML 14 and MEI. The individual formats are each suitable for a different purpose: for instance, MIDI is most useful for interfacing different electronic audio devices, MEI is great for editorial work, LilyPond allows for excellent control of music engraving.…”

Section: A Interfaces In the Omr Pipelinementioning

confidence: 99%

In Search of a Dataset for Handwritten Optical Music Recognition: Introducing MUSCIMA++

Hajič,

Pecina

2017

Preprint

View full text Add to dashboard Cite

Optical Music Recognition (OMR) has long been without an adequate dataset and ground truth for evaluating OMR systems, which has been a major problem for establishing a state of the art in the field. Furthermore, machine learning methods require training data. We analyze how the OMR processing pipeline can be expressed in terms of gradually more complex ground truth, and based on this analysis we present the MUSCIMA++ dataset of handwritten music notation that addresses musical symbol recognition and notation reconstruction. The MUSCIMA++ dataset v.0.9 consists of 140 pages of handwritten music, with 91255 manually annotated notation symbols and 82261 explicitly marked relationships between symbol pairs. The dataset allows training and evaluating models for symbol classification, symbol localization, and notation graph assembly, both in isolation and jointly. Open-source tools are provided for manipulating the dataset, visualizing the data and annotating further, and the dataset itself is made available under an open license.

show abstract

“…But they focused on only a few classes of the music symbols. [ 3 ] developed an algorithm to learn a Mahalanobis distance for the k-NNs and extended it to SVMs. However the classification accuracy was below 80% In some instances, the operation of symbol classification was linked to the segmentation of objects from the music symbols.…”

Section: Related Workmentioning

confidence: 99%

A Directed Acyclic Graph-Large Margin Distribution Machine Model for Music Symbol Classification

et al. 2016

View full text Add to dashboard Cite

Optical Music Recognition (OMR) has received increasing attention in recent years. In this paper, we propose a classifier based on a new method named Directed Acyclic Graph-Large margin Distribution Machine (DAG-LDM). The DAG-LDM is an improvement of the Large margin Distribution Machine (LDM), which is a binary classifier that optimizes the margin distribution by maximizing the margin mean and minimizing the margin variance simultaneously. We modify the LDM to the DAG-LDM to solve the multi-class music symbol classification problem. Tests are conducted on more than 10000 music symbol images, obtained from handwritten and printed images of music scores. The proposed method provides superior classification capability and achieves much higher classification accuracy than the state-of-the-art algorithms such as Support Vector Machines (SVMs) and Neural Networks (NNs).

show abstract

Metric Learning for Music Symbol Recognition

Cited by 9 publications

References 16 publications

Deep Multilevel Cascade Residual Recurrent Framework (MCRR) for Sheet Music Recognition

Deep Multilevel Cascade Residual Recurrent Framework (MCRR) for Sheet Music Recognition

In Search of a Dataset for Handwritten Optical Music Recognition: Introducing MUSCIMA++

A Directed Acyclic Graph-Large Margin Distribution Machine Model for Music Symbol Classification

Contact Info

Product

Resources

About