A shortest path approach for staff line detection

Ana Rebelo, Carlos Guedes, Artur Capela, Eurico Carrapatoso, Joaquim F. Pinto Da Costa, Jaime S. Cardoso

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many music works produced in the past still exist only as original manuscripts or as photocopies. Preserving them entails their digitalization and consequent accessibility in a digital format easy-to-manage. The manual process to carry out this task is very time consuming and error prone. Optical music recognition (OMR) is a form of structured document image analysis where music symbols are isolated and identified so that the music can be conveniently processed. While OMR systems perform well on printed scores, current methods for reading handwritten musical scores by computers remain far from ideal. One of the fundamental stages of this process is the staff line detection. In this paper a new method for the automatic detection of music stave lines based on a shortest path approach is presented. Lines with some curvature, discontinuities, and inclination are robustly detected. The proposed algorithm behaves favourably when compared experimentally with well-established algorithms.

Original languageEnglish (US)
Title of host publicationProceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007
Pages79-85
Number of pages7
DOIs
StatePublished - Dec 1 2007
Event3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007 - Barcelona, Spain
Duration: Nov 28 2007Nov 30 2007

Other

Other3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007
CountrySpain
CityBarcelona
Period11/28/0711/30/07

Fingerprint

Image analysis

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Rebelo, A., Guedes, C., Capela, A., Carrapatoso, E., Pinto Da Costa, J. F., & Cardoso, J. S. (2007). A shortest path approach for staff line detection. In Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007 (pp. 79-85). [4402863] https://doi.org/10.1109/AXMEDIS.2007.16

A shortest path approach for staff line detection. / Rebelo, Ana; Guedes, Carlos; Capela, Artur; Carrapatoso, Eurico; Pinto Da Costa, Joaquim F.; Cardoso, Jaime S.

Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007. 2007. p. 79-85 4402863.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rebelo, A, Guedes, C, Capela, A, Carrapatoso, E, Pinto Da Costa, JF & Cardoso, JS 2007, A shortest path approach for staff line detection. in Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007., 4402863, pp. 79-85, 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007, Barcelona, Spain, 11/28/07. https://doi.org/10.1109/AXMEDIS.2007.16
Rebelo A, Guedes C, Capela A, Carrapatoso E, Pinto Da Costa JF, Cardoso JS. A shortest path approach for staff line detection. In Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007. 2007. p. 79-85. 4402863 https://doi.org/10.1109/AXMEDIS.2007.16
Rebelo, Ana ; Guedes, Carlos ; Capela, Artur ; Carrapatoso, Eurico ; Pinto Da Costa, Joaquim F. ; Cardoso, Jaime S. / A shortest path approach for staff line detection. Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007. 2007. pp. 79-85
@inproceedings{a5595deb7daa40b19b626c1bfa80525f,
title = "A shortest path approach for staff line detection",
abstract = "Many music works produced in the past still exist only as original manuscripts or as photocopies. Preserving them entails their digitalization and consequent accessibility in a digital format easy-to-manage. The manual process to carry out this task is very time consuming and error prone. Optical music recognition (OMR) is a form of structured document image analysis where music symbols are isolated and identified so that the music can be conveniently processed. While OMR systems perform well on printed scores, current methods for reading handwritten musical scores by computers remain far from ideal. One of the fundamental stages of this process is the staff line detection. In this paper a new method for the automatic detection of music stave lines based on a shortest path approach is presented. Lines with some curvature, discontinuities, and inclination are robustly detected. The proposed algorithm behaves favourably when compared experimentally with well-established algorithms.",
author = "Ana Rebelo and Carlos Guedes and Artur Capela and Eurico Carrapatoso and {Pinto Da Costa}, {Joaquim F.} and Cardoso, {Jaime S.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/AXMEDIS.2007.16",
language = "English (US)",
isbn = "0769530303",
pages = "79--85",
booktitle = "Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007",

}

TY - GEN

T1 - A shortest path approach for staff line detection

AU - Rebelo, Ana

AU - Guedes, Carlos

AU - Capela, Artur

AU - Carrapatoso, Eurico

AU - Pinto Da Costa, Joaquim F.

AU - Cardoso, Jaime S.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Many music works produced in the past still exist only as original manuscripts or as photocopies. Preserving them entails their digitalization and consequent accessibility in a digital format easy-to-manage. The manual process to carry out this task is very time consuming and error prone. Optical music recognition (OMR) is a form of structured document image analysis where music symbols are isolated and identified so that the music can be conveniently processed. While OMR systems perform well on printed scores, current methods for reading handwritten musical scores by computers remain far from ideal. One of the fundamental stages of this process is the staff line detection. In this paper a new method for the automatic detection of music stave lines based on a shortest path approach is presented. Lines with some curvature, discontinuities, and inclination are robustly detected. The proposed algorithm behaves favourably when compared experimentally with well-established algorithms.

AB - Many music works produced in the past still exist only as original manuscripts or as photocopies. Preserving them entails their digitalization and consequent accessibility in a digital format easy-to-manage. The manual process to carry out this task is very time consuming and error prone. Optical music recognition (OMR) is a form of structured document image analysis where music symbols are isolated and identified so that the music can be conveniently processed. While OMR systems perform well on printed scores, current methods for reading handwritten musical scores by computers remain far from ideal. One of the fundamental stages of this process is the staff line detection. In this paper a new method for the automatic detection of music stave lines based on a shortest path approach is presented. Lines with some curvature, discontinuities, and inclination are robustly detected. The proposed algorithm behaves favourably when compared experimentally with well-established algorithms.

UR - http://www.scopus.com/inward/record.url?scp=47849092785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47849092785&partnerID=8YFLogxK

U2 - 10.1109/AXMEDIS.2007.16

DO - 10.1109/AXMEDIS.2007.16

M3 - Conference contribution

AN - SCOPUS:47849092785

SN - 0769530303

SN - 9780769530307

SP - 79

EP - 85

BT - Proceedings - 3rd International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, AXMEDIS 2007

ER -