Analysis and Recognition of Music Scores

Fornés, Alícia; Sánchez, Gemma

doi:10.1007/978-0-85729-859-1_24

Cited by 14 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OMR studies by [1] or [2] typically present the OMR workflow as multiple consecutive stages: image preprocessing, staff detection with possible removal, music symbol segmentation/classification and finally music notation reconstruction. However, many works reorganize, merge or remove some of these stages.…”

Section: A Optical Music Recognitionmentioning

confidence: 99%

“…Symbol Detection: Music scores are constructed using a lot of relatively simple shapes like lines and blobs in a complex bi-dimensional structure. This fact has pushed OMR systems to use simple extraction algorithm like graphical primitive detection or connected components, and then use complex adhoc rules to merge or over-segment primitives [1]. The classification of music symbols can be done using a variety of techniques like simple filters, template matching or classifiers like HMM, neural network, K-NN and SVM as presented in [5].…”

Section: A Optical Music Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

CNN-Based Accidental Detection in Dense Printed Piano Scores

Choi

Coüasnon²,

Ricquebourg

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

The recognition of mid-18th to mid-20th century piano scores presents segmentation challenges caused by touching and broken symbols produced by imprinting techniques and time degradation. We present a new notehead accidental dataset containing 2955 images from dense and damaged piano scores. We address this detection problem with very small training samples using a simple Spatial Transformer (ST)-based Convolutional Neural Network detector improved through bootstrapping and contextual information, and more powerful deep learning detectors (Faster R-CNN, R-FCN, and SSD) with transfer-learning on the COCO dataset. We trained all our detectors using 5 fold cross-validation and obtain 98.73% mean Average Precision (mAP) for an Intersection over Union (IoU) threshold of 0.75 with our best detector. Our STbased detector obtains a slightly lower mAP of 94.81%, but runs 40 times faster, and uses 18 times less memory.

show abstract

Section: A Optical Music Recognitionmentioning

confidence: 99%

Section: A Optical Music Recognitionmentioning

confidence: 99%

CNN-Based Accidental Detection in Dense Printed Piano Scores

Choi

Coüasnon²,

Ricquebourg

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

show abstract

“…MusicXML, MEI, MIDI, etc.). It has been an active research field for more than five decades [1,2], and there are many commercial OMR software such as PhotoScore 1 or SharpEye 2 with good performance under relatively good conditions. However, their accuracy dramatically decreases when dealing with handwritten scores, mainly because of the high variability in the handwriting style.…”

Section: Introductionmentioning

confidence: 99%

From Optical Music Recognition to Handwritten Music Recognition: A baseline

Baró

Riba

Calvo-Zaragoza

et al. 2019

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

Optical Music Recognition (OMR) is the branch of document image analysis that aims to convert images of musical scores into a computer-readable format. Despite decades of research, the recognition of handwritten music scores, concretely the Western notation, is still an open problem, and the few existing works only focus on a specific stage of OMR. In this work, we propose a full Handwritten Music Recognition (HMR) system based on Convolutional Recurrent Neural Networks, data augmentation and transfer learning, that can serve as a baseline for the research community.

show abstract

“…We take advantage of the fact that position of the note head is known, and use the centroid position of the note head as a feature. b) Accidental Localization: OMR systems break down the process of recognizing a music scores into multiple steps [1]. First, preprocessing techniques, like binarization, are used to prepare the image.…”

mentioning

confidence: 99%