A Morphological Method for Music Score Staff Removal

From LRDE

Abstract

Removing the staff in music score images is a key to improve the recognition of music symbols and, with ancient and degraded handwritten music scores, it is not a straightforward task. In this paper we present the method that has won in 2013 the staff removal competitionorganized at the International Conference on Document Analysis and Recognition (ICDAR). The main characteristics of this method is that it essentially relies on mathematical morphology filtering. So it is simple, fastand its full source code is provided to favor reproducible research.

Documents


Figure

.

Step-by-step staff removal: the same image excerpt is depicted: click on the images to enlarge.

.


Geraud14icip input.png
(a) Input image.


Geraud14icip step1.png
(b) Step 1: permissive hit-or-miss.


Geraud14icip step2.png
(c) Step 2: horizontal median filter.


Geraud14icip step3.png
(d) Step 3: horizontal reconstruction.


Geraud14icip step4.png
(e) Step 4: cleaning.


Geraud14icip step5s.png
(f) Step 5: after line selection (contour superimposed).


Geraud14icip output.png
(g) Step 6: output, after a local vertical median filter.


Geraud14icip groundtruth.png
(h) Ground truth.

Source Code

Code of the method described in the paper: [1]


Useful Links

  • The staff removal competition organized at the International Conference on Document Analysis and Recognition (ICDAR) 2013:

http://www.icdar2013.org/program/competitions

  • The CVC-MUSCIMA database of handwritten music score images:

http://www.cvc.uab.es/cvcmuscima

  • The Olena Image Processing Platform (containing the Milena C++ image processing library):

http://olena.lrde.epita.fr

  • An online demo of staff removal:

http://olena.lrde.epita.fr/demos/staff_removal.php


Contact

Bibtex (lrde.bib)

@InProceedings{	  geraud.14.icip,
  author	= {Thierry G\'eraud},
  title		= {A Morphological Method for Music Score Staff Removal},
  booktitle	= {Proceedings of the 21st International Conference on Image
		  Processing (ICIP)},
  year		= 2014,
  address	= {Paris, France},
  pages		= {2599--2603},
  abstract	= {Removing the staff in music score images is a key to
		  improve the recognition of music symbols and, with ancient
		  and degraded handwritten music scores, it is not a
		  straightforward task. In this paper we present the method
		  that has won in 2013 the staff removal competition,
		  organized at the International Conference on Document
		  Analysis and Recognition (ICDAR). The main characteristics
		  of this method is that it essentially relies on
		  mathematical morphology filtering. So it is simple, fast,
		  and its full source code is provided to favor reproducible
		  research.}
}