Optical music recognition
This article needs additional citations for verification. (November 2015) (Learn how and when to remove this template message)
Optical music recognition (OMR) or Music OCR is the application of optical character recognition to interpret sheet music or printed scores into editable or playable form. Once captured digitally, the music can be saved in commonly used file formats, e.g. MIDI (for playback) and MusicXML (for page layout).
Early research into recognition of printed sheet music was performed at the graduate level in the late 1960s at MIT and other institutions. Successive efforts were made to localize and remove musical staff lines leaving symbols to be recognized and parsed. The first commercial music-scanning product, MIDISCAN (now SmartScore), was released in 1991 by Musitek corporation.
Unlike OCR of text, where words are parsed sequentially, music notation involves parallel elements, as when several voices are present along with unattached performance symbols positioned nearby. Therefore, the spatial relationship between notes, expression marks, dynamics, articulations and other annotations is an important part of the expression of the music.
This section relies too much on references to primary sources. (March 2016) (Learn how and when to remove this template message)
- ForteScan Light by Fortenotation
- MIDI-Connections Scan by MIDI-Connections
- MP Scan by Braeburn. Uses SharpEye SDK.
- NoteScan bundled with Nightingale
- OMeR (Optical Music easy Reader) Add-on for Harmony Assistant and Melody Assistant: Myriad Software (ShareWare)
- PhotoScore by Neuratron. The Light version of PhotoScore is used in Sibelius. PhotoScore uses the SharpEye SDK.
- ScoreMaker by Kawai
- Scorscan by npcImaging. Based on SightReader(?)
- SharpEye By Visiv
- VivaldiScan (same as SharpEye)
- SmartScore By Musitek. Formerly packaged as "MIDISCAN". (SmartScore Lite is used in Finale).
Free/open source software
Similar but different
PDFtoMUSIC by Myriad is often seen as a Music OCR software, but it does actually no optical character recognition. The program simply reads PDF files which have been created by some scorewriter, locates the musical glyphs which have been written directly as characters of a music notation font. The optical recognition consists of concluding the musical relationship of those glyphs from their relative position in space, i.e. on the logical page of the PDF document, and combine those to a musical score. Only the PRO version can export this to a MusicXML file, while the standard version works only for the scorewriters by Myriad.
- Music information retrieval (MIR) is the broader problem of retrieving music information from media including music scores and audio.
- Optical character recognition (OCR) is the recognition of text which can be applied to document retrieval, analogously to OMR and MIR. However, a complete OMR system must faithfully represent text that is present in music scores, so OMR is in fact a superset of OCR.
- Pruslin, Dennis Howard (1966). "Automatic Recognition of Sheet Music". Perspectives of New Music. 11 (1): 250–254. JSTOR 832471.
- Info capella-scan
- FORTE Scan Light Archived 2013-09-22 at the Wayback Machine
- MIDI-Connections SCAN 2.0 Archived 2013-12-20 at the Wayback Machine
- Music Publisher Scanning Edition
- PhotoScore Ultimate 7
- Scoremaker (Japanese) Archived 2013-10-08 at Archive.today
- SmartScore Archived 2012-04-17 at the Wayback Machine
- Audiveris - Github page
- "PDFtoMusic Pro". myriad-online.com. 2015. Retrieved 13 November 2015.
- Bainbridge, David; Bell, Tim (2001). "The challenge of optical music recognition". Computers and the Humanities. 35 (2): 95–121. doi:10.1023/A:1002485918032. Retrieved 23 February 2017.
- Optical Music Recognition (OMR): Programs and scientific papers
- Optical Music Recognition Bibliography: A comprehensive list of papers published in OMR.
- OMR (Optical Music Recognition) Systems: Comprehensive table of OMR (Last updated: 30 Jan. 2007).
- Assessing Optical Music Recognition Tools Authors: Pierfrancesco Bellini, Ivan Bruno, Paolo Nesi
- Optical Manuscript Analysis University of Leeds research project.