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:

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

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

  • An online demo of staff removal: