[MEI-L] Tools/libraries to find staves in scanned sheet music

[Urs Liska]

Hi Andrew (and David Lewis),

thank you for the reference.
For the project at hand I'm not so much interested in a way to
reimplement algorithms but rather in tools that can be used in a
scripted environment. So probably I'll rather have a closer look at
Audiveris.

But such a library, especially as Python, is definitely something very
interesting regarding my longer-term ideas for Frescobaldi. I'm shocked
to see how long it has been since we added the manuscript viewer to it,
but it had always been my plan to push it more into the direction of an
editorial tool (in the sense of music editing vs. code editing).

Best
Urs


Am Donnerstag, den 30.04.2020, 16:12 +0000 schrieb Andrew Hankinson:
> I think the most current algorithm implemented in the MusicStaves
> toolkit is the Stable Paths algorithm (we implemented it at McGill a
> few years back):
> 
> https://gamera.informatik.hsnr.de/addons/musicstaves/doc/gamera.toolkits.musicstaves.stafffinder_stable_path.StaffFinder_stable_path.html
> 
> You can download the source code here:
> 
> https://gamera.informatik.hsnr.de/addons/musicstaves/
> 
> The classes are described here:
> 
> https://gamera.informatik.hsnr.de/addons/musicstaves/doc/plugins.html
> 
> If you don't want to get Gamera running to use them, the papers are
> referenced in the documentation and you should be able to re-
> implement the algorithms in the language of your choice from the
> Python code.
> 
> -Andrew
> 
> > On 30 Apr 2020, at 16:42, David Lewis <D.Lewis at gold.ac.uk> wrote:
> > 
> > Hi Urs,
> > 
> > One thing that no one has mentioned yet, but used to do quite well
> > is the Gamera toolkit's MusicStaves add-on. It's quite old now, so
> > unlikely to be state-of-the-art. Although it can remove staves,
> > that doesn't need to be part of your workflow. 
> > 
> > I don't know if any lurkers on the list know anything about its
> > current status, but the homepage is:
> > https://gamera.informatik.hsnr.de/index.html 
> > 
> > Best,
> > 
> > David
> > 
> > 
> > 
> > > On 30 Apr 2020, at 08:41, Urs Liska <ul at openlilylib.org> wrote:
> > > 
> > > Dear MEI,
> > > 
> > > I am investigating ways to produce empty staves/barlines to
> > > overlay
> > > over scanned sheet music. The use case is creating
> > > teaching/testing
> > > sheets for music theory and aural training classes (so the target
> > > repertoire would be mostly common western notation).
> > > 
> > > My first approach was to create a Scribus script that draws
> > > staff- and
> > > barlines from rectangles that have been drawn over the systems.
> > > While
> > > this works surprisingly well it is still a tedious work for
> > > longer and
> > > full scores.
> > > 
> > > AFAIK the detection of staff- and barlines is basically a solved
> > > challenge in OMR. Could somebody point me towards the potentially
> > > easiest approach I should explore? Algorithms, libraries, ready-
> > > to-use
> > > tools?
> > > 
> > > What I need is something that analyses (multipage) sheet music
> > > from
> > > image or PDF files and produces a structured text file with all
> > > the
> > > relevant coordinates, or anything from which I can instruct some
> > > tool
> > > (whether Inkscape, Scribus, LilyPond or whatever) to generate the
> > > empty
> > > sheet music to overlay over the scanned score.
> > > 
> > > Thank you for any pointers
> > > Urs
> > > 
> > > PS: Do you agree with me that trying to somehow *remove* the
> > > musical
> > > content from a scanned image is a much less promising approach?
> > > 
> > > 
> > > _______________________________________________
> > > mei-l mailing list
> > > mei-l at lists.uni-paderborn.de
> > > https://lists.uni-paderborn.de/mailman/listinfo/mei-l
> > 
> > _______________________________________________
> > mei-l mailing list
> > mei-l at lists.uni-paderborn.de
> > https://lists.uni-paderborn.de/mailman/listinfo/mei-l
> 
> _______________________________________________
> mei-l mailing list
> mei-l at lists.uni-paderborn.de
> https://lists.uni-paderborn.de/mailman/listinfo/mei-l