The OMR Introduction-What is OMR?

by | Jan 23, 2018

Optical music recognition (OMR) is the music equivalent of optical character recognition (OCR). This technology applies OCR to interpret digital sheet music and scanned scores into editable or playable form. Once captured digitally, the music can be saved in commonly used file formats, such as MIDI (for playback) and MusicXML (for page layout).

OMR can be extremely useful for transposing, rearranging and extracting parts in a notation software.

I) What is OMR?

Early research conducted into the recognition of printed sheet music was performed at graduate level in the late 1960s at the Massachusetts Institute of Technology (MIT) and other institutions. Successive efforts were made to localize and remove musical staff lines leaving symbols to be recognized and parsed. Since then, more and more platforms are creating their very own home-made OMR technologies.

In this chapter, we will introduce the two main products that fully feature OMR: Photoscore (by Neutraton) and Smartscore (by Musitek).

Both these products enable users to recognize sheet music and convert it into MusicXML, and come with a host of editing features. Both continuously develop and improve their main software, while innovating with complementary products.

Neutraton has recently developed a notation application called Notateme to create a powerful bridge between paper sheet music and editable digital scores. The direct integration of those scores into Sibelius offers an improved workflow for Sibelius users who wish to edit their scanned piece.

Musitek created a “converter box” called SmartScore Music-to-XML. We asked Philip Rothmann, editor and principal contributor of the Scoring Notes blog, to share his thoughts on the SmartScore Music-to-XML converter.

“Music-to-XML is, essentially, a “black box” that intakes PDFs (or TIFF image files) and outputs music notation files in the MusicXML interchange format. It can optionally bypass the step of saving the MusicXML file to your hard drive and instead send it directly to Finale, Sibelius or Dorico.

Unlike its big brother SmartScore X2 Pro or SmartScore’s main competitor, Neuratron’s PhotoScore Ultimate, there is no music editing capability in Music-to-XML. You can’t actually open and view a file with Music-to-XML; you can’t resolve errors, extract parts, delete items, change page size, transpose, print it, play it back or export audio. Music-to-XML is only useful if you have a music notation program to work with, while the more full-featured programs like SmartScore X2 Pro and PhotoScore Ultimate can be used as stand-alone products.

Once recognition is completed, Music-to-XML offers to send it directly to Finale, Sibelius or Dorico, or save it as a MusicXML file, as described above.

If you have reasonable facility with any music notation software that opens MusicXML (including not just Finale, Sibelius or Dorico, but those to which Music-to-XML doesn’t directly transfer the file, like MuseScore or Notion), and you have even the occasional need to work with importing music from PDFs, Music-to-XML is real value for money, but you need to heed the advice in the following section, when is it relevant to use OMR?”

Philip Rothman

Scoring Notes

II) When is it Relevant to Use OMR?

Before you start working with OMR, it’s very important to keep in mind that the accuracy of the score recognition will mostly depend on the score’s structure. Below, we have listed the most important and common requirements before being able to use any OMR product. If your score doesn’t respect all of these conditions, we strongly recommend that you write the piece from scratch.

Sheet Music Specificities to Use OMR

  • Larger fonts with crisper, more detailed printing will have better accuracy than smaller.

  • Avoid scores with broken, faded or segmented note stems and staff lines.

  • OMR software requires an image where the vertical distance between staff lines is at least 9 pixels.
  • A straightened score with a white margin of at least 1/4 to 1/2 inch is ideal.

  • It is especially important to keep the left- and right-hand margins of every system within the borders of the scanned image and to avoid light leaks (masses of black) onto the image area containing the music.

  • A maximum of 30-35 pages is recommended.  
  • Handwritten scores are still not accurately recognized.

  • Thus, parts or full scores with handwritten markings will not be accurately reproduced.
  • In terms of resolution, 300 to 400 DPI is the minimum for A4-B4 formats. For larger scores, we recommend 600 DPI.

  • Also, scanning in grayscale will be more accurate.

  • Lastly, darkening the final scan will thicken these lines and increase recognition accuracy.
  • III) What are the Challenges of OMR?

    The Technical Complexity of OMR

    Unlike OCR, where characters are analyzed sequentially, OMR has a much more complex task; as music notation involves parallel and interdependent elements. Therefore, the spatial relationship between notes, expression marks, dynamics, articulations and other annotations make it extremely challenging to make this technique 100% accurate and reliable. Indeed, in some cases, it will be safer and quicker to write the music from scratch rather than using an OMR product. That is why we wanted to explore and share with you the ideal scenarios to get the most out of this technology.

    Here, Philip Rothman gives his thoughts and expertise on OMR:

    “You’ll most likely find OMR useful, say, if you do a lot of arranging where you’re not so concerned with the total accuracy of the result, but you need to quickly get the essence of a piece of music into your preferred software so that you can spend more time creatively working with it and less time on the rote mechanics of note entry. Another obvious case is if you work with relatively straightforward charts for which you already own the music and need to often transpose them into another key for a particular vocalist. Generally speaking, the clearer and easier the music is to read, the better the output will be. Simpler music will fare better than more complex music. Lyrics and chord symbols are less reliable.”

    Philip Rothman

    Scoring Notes

    Copyright issues

    This technology raises a lot of new questions linked with copyright, since it allows any individual to buy or scan a piece of sheet music, use the OMR and re-edit the music into his notation software without permission. On this subject, Philip Rothman shared an interesting anecdote on his Scoring Notes blog, regarding MakeMusic 2016’s announcement to include this technology and directly import editable PDF into Finale 25:

    “One prominent composer predicted lawsuits over the feature along with “the collapse of music sales”. This misguided opinion gained a following on social media, and in light of the brouhaha, MakeMusic decided to pull the feature prior to the release of Finale 25.

    Nevertheless, the music recognition technology which had been available all along remained so. Musitek, the maker of that technology, has released it as a separate $100 product called SmartScore Music-to-XML that will do the exact same thing as what was planned for inclusion in Finale: take a PDF containing scanned music and convert for use in music notation software.”

    Philip Rothman

    Scoring Notes

    Long story short, our conclusion is that OMR is like any other technology: powerful and neutral. It is up to the users to make sure that they are using this technology for their own compositions, responsibly and legally.