Corpus ID: 4531457

One-Step Detection of Background, Staff Lines, and Symbols in Medieval Music Manuscripts with Convolutional Neural Networks

@inproceedings{CalvoZaragoza2017OneStepDO,
  title={One-Step Detection of Background, Staff Lines, and Symbols in Medieval Music Manuscripts with Convolutional Neural Networks},
  author={Jorge Calvo-Zaragoza and Gabriel Vigliensoni and Ichiro Fujinaga},
  booktitle={ISMIR},
  year={2017}
}
One of the most complex stages of optical music recognition workflows is the detection and isolation of musical symbols. [...] Key Method Our proposal classifies each pixel of the image among background, staff lines, and symbols using supervised learning techniques, namely convolutional neural networks. Experiments on a set of medieval music pages proved that the proposed approach is very accurate, achieving a performance upwards of 90% and outperforming common ensembles of binarization and staffline removal…Expand
Understanding Optical Music Recognition
DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images
Musical-Linguistic Annotations of Il Lauro Secco
Multimodal Optical Music Recognition using Deep Learning
  • 2020
Evaluating Simultaneous Recognition and Encoding for Optical Music Recognition

References

SHOWING 1-10 OF 28 REFERENCES
Music staff removal with supervised pixel classification
A morphological method for music score staff removal
  • T. Géraud
  • Computer Science
  • 2014 IEEE International Conference on Image Processing (ICIP)
  • 2014
An Efficient Staff Removal Approach from Printed Musical Documents
A Machine Learning Based Method for Staff Removal
Lyric Extraction and Recognition on Digital Images of Early Music Sources
Music Score Binarization Based on Domain Knowledge
An Effective Staff Detection and Removal Technique for Musical Documents
Optical music recognition: state-of-the-art and open issues
...
1
2
3
...