Automatic Score Extraction with Optical Music Recognition (OMR)

  • Ichiro FujinagaEmail author
  • Andrew Hankinson
  • Laurent Pugin
Part of the Springer Handbooks book series (SHB)


Optical music recognition (OMR ) describes the process of automatically transcribing music notation from a digital image. Although similar to optical character recognition (OCR ), the process and procedures of OMR diverge due to the fundamental differences between text and music notation, such as the two-dimensional nature of the notation system and the overlay of music symbols on top of staff lines. The OMR process can be described as a sequence of steps, with techniques adapted from disciplines including image processing, machine learning, grammars, and notation encoding. The sequence and specific techniques used can differ depending on the condition of the image, the type of notation, and the desired output.

Several commercial and open-source OMR software systems have been available since the mid-1990s. Most of them are designed to be used by individuals and recognize common (post-18th-century) Western music notation, though there have been some efforts to recognize other types of music notation such as for the lute and for earlier Western music.

Even though traditional applications of OMR have focused on small-scale recognition tasks, typically as an automated method of musical entry for score editing, new applications of large-scale OMR are under development, where automated recognition is the central technology for building full-music search systems, similar to the large-scale full-text recognition efforts.




American standard code for information interchange






common Western music notation


digital alternative representation of music scores


Essen associative code


general public license


hidden Markov model


hyper-text markup language


maximum a posteriori


musical instrument digital interface


notation interchange file format


neural network


optical character recognition


one document does it all


optical music recognition


  1. 16.1
    D.H. Shepard: Apparatus for reading, Patent Application 2664758 (1951)Google Scholar
  2. 16.2
    D. Martin: David H. Shepard, 84, Dies; Optical Reader Inventor, New York Times, 11 December 2007Google Scholar
  3. 16.3
    D. Pruslin: Automatic Recognition of Sheet Music, Sc. D. Diss. (Massachusetts Institute of Technology, Cambridge 1966)Google Scholar
  4. 16.4
    D. Prerau: Computer Pattern Recognition of Standard Engraved Music Notation, PhD Diss. (Massachusetts Institute of Technology, Cambridge 1970)Google Scholar
  5. 16.5
    A. Samuel: The banishment of paper-work, New Sci. 21(380), 529–530 (1964)Google Scholar
  6. 16.6
    S. Mori, C. Suen, K. Yamamoto: Historical review of OCR research and development, Proc. IEEE 80(7), 1029–1058 (1992)CrossRefGoogle Scholar
  7. 16.7
    D.S. Prerau: Computer pattern recognition of printed music. In: Fall Joint Computer Conference 1971, AFIP Conf. Proc., Vol. 39 (1971) pp. 153–162Google Scholar
  8. 16.8
    D. Blostein, H.S. Baird: A critical survey of music image analysis. In: Structured Document Image Analysis, ed. by H.S. Baird, H. Bunke, K. Yamamoto (Springer, Berlin 1992) pp. 405–434CrossRefGoogle Scholar
  9. 16.9
    C. Dalitz, T. Karsten: Using the Gamera framework for building a lute tablature recognition system. In: 6th Int. Soc. Music Inf. Retr. Conf. (ISMIR) (2005) pp. 478–481Google Scholar
  10. 16.10
    L.L. Wei, Q.A. Salih, H.S. Hock: Optical tablature recognition (OTR) system: Using Fourier descriptors as a recognition tool. In: 2008 International Conference on Audio, Language and Image Processing, Shanghai (2008) pp. 1532–1539, CrossRefGoogle Scholar
  11. 16.11
    C. Dalitz, C. Pranzas: German lute tablature recognition. In: Int. Conf. Document Anal. Recognit. (ICDAR) (2009) pp. 371–375Google Scholar
  12. 16.12
    V.G. Gezerlis, S. Theodoridis: Optical character recognition of the orthodox hellenic byzantine music notation, Pattern Recognit. 35(4), 895–914 (2002)CrossRefGoogle Scholar
  13. 16.13
    C. Dalitz, G.K. Michalakis, C. Pranzas: Optical recognition of psaltic Byzantine chant notation, Int. J. Doc. Anal. Recognit. (IJDAR) 11(3), 143–158 (2008)CrossRefGoogle Scholar
  14. 16.14
    L. Pugin: Optical music recognition of early typographic prints using hidden Markov models. In: 7th Int. Conf. Music Inf. Retr. (ISMIR) (2006) pp. 53–56Google Scholar
  15. 16.15
    L. Tardón, S. Sammartino, I. Barbancho, V. Gómez, A. Oliver: Optical music recognition for scores written in white mensural notation, EURASIP J. Image Video Process. 2009, 843401 (2009), CrossRefGoogle Scholar
  16. 16.16
    D. Bainbridge: Extensible Optical Music Recognition, PhD Diss. (University of Canterbury, Canterbury 1997)Google Scholar
  17. 16.17
    K. MacMillan, M. Droettboom, I. Fujinaga: Gamera: Optical music recognition in a new shell. In: Proc. Int. Comput. Music Conf. (2002) pp. 482–485zbMATHGoogle Scholar
  18. 16.18
    D. Marr: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information (Freeman, New York 1982)Google Scholar
  19. 16.19
    T. Pun: C. De. Garrini: Cybernétique et vision par ordinateur. In: Le déficit visuel, de la neurophysiologie à la pratique de la réadaptation, ed. by A.B. Safran, A. Assimacopoulos (Masson, Paris 2014) pp. 213–224Google Scholar
  20. 16.20
    R. Bruyer: Le Cerveau Qui Voit (Editions Odile Jacob, Paris 2000)Google Scholar
  21. 16.21
    A. Rebelo, I. Fujinaga, F. Paszkiewicz, A.R.S. Marcal, C. Guedes, J.S. Cardoso: Optical music recognition: State-of-the-art and open issues, Int. J. Multimed. Inf. Retr. 1(3), 173–190 (2012)CrossRefGoogle Scholar
  22. 16.22
    K.M. Sayre: Machine recognition of handwritten words: A project report, Pattern Recognit. 5, 213–228 (1973)CrossRefGoogle Scholar
  23. 16.23
    T. Plötz, G. Fink: Markov models for offline handwriting recognition: A survey, Int. J. Document Anal. Recognit. 12, 269 (2009)CrossRefGoogle Scholar
  24. 16.24
    K.C. Ng, R.D. Boyle: Recognition and reconstruction of primitives in music scores, Image Vis. Comput. 14(1), 39–46 (1996)CrossRefGoogle Scholar
  25. 16.25
    I. Fujinaga, J. Riley: Recommended best practices for digital image capture of musical scores. In: 3rd Int. Conf. Music Inf. Retr. (ISMIR) (2002) pp. 261–263Google Scholar
  26. 16.26
    W. Koseluk: Digitalization of musical sources: An overview. In: The Virtual Score: Representation, Retrieval, Restoration, Computing in Musicology, Vol. 12, ed. by W.B. Hewlett, E. Selfridge-Field (MIT Press, Cambridge 2001) pp. 219–226Google Scholar
  27. 16.27
    D. Bainbridge, T. Bell: The challenge of optical music recognition, Comput. Humanit. 35, 95–121 (2001)CrossRefGoogle Scholar
  28. 16.28
    E. Selfridge-Field: Optical recognition of musical notation: A survey of current work. In: Computational Musicology: An International Directory of Applications, Vol. 9, ed. by W.B. Hewlett, E. Selfridge-Field (1993) pp. 109–146Google Scholar
  29. 16.29
    P. Martin, C. Bellissant: Low-level analysis of music drawings. In: 1st Int, Conf. Doc. Anal. Recognit., ICDAR pp, 417–425 (1991)Google Scholar
  30. 16.30
    H. Fahmy, D. Blostein: A graph grammar programming style for recognition of music notation, Mach. Vis. Appl. 6, 83–99 (1993)CrossRefGoogle Scholar
  31. 16.31
    D. Bainbridge, T. Bell: A music notation construction engine for optical music recognition, Softw. Pract. Exp. 33(2), 173–200 (2003)CrossRefGoogle Scholar
  32. 16.32
    K. MacMillan, M. Droettboom, I. Fujinaga: Gamera: A structured document recognition application development environment. In: 2nd Int. Symp. Music Inf. Retr. ISMIR (2001) pp. 173–178Google Scholar
  33. 16.33
    K.C. Ng: Music manuscript tracing. In: 4th Int. Workshop, Graphics Recognit.: Algorithms and Applications (GREC) (2001) pp. 322–334Google Scholar
  34. 16.34
    J. Burgoyne, L. Pugin, G. Eustace, I. Fujinaga: A comparative survey of image binarisation algorithms for optical recognition on degraded musical sources. In: 8th Int. Conf. Music Inf. Retr. (ISMIR) (2007) pp. 509–512Google Scholar
  35. 16.35
    C. Dalitz, M. Droettboom, B. Pranzas, I. Fujinaga: A comparative study of staff removal algorithms, IEEE Trans. Pattern Anal. Mach. Intell. 30(5), 753–766 (2008)CrossRefGoogle Scholar
  36. 16.36
    H. Miyao: Stave extraction for printed music scores. In: 3rd Int. Conf. Intell. Data Eng. Automated Learning (IDEAL) (2002) pp. 562–568Google Scholar
  37. 16.37
    F. Rossant: A global method for music symbol recognition in typeset music sheets, Pattern Recognit. Lett. 23(10), 1129–1141 (2002)CrossRefGoogle Scholar
  38. 16.38
    I. Fujinaga: Exemplar-based learning in adaptive optical music recognition system. In: Int. Comput. Music Conf (1996) pp. 55–60Google Scholar
  39. 16.39
    H. Kato, S. Inokuchi: A recognition system for printed piano music using musical knowledge and constraints. In: Int. Assoc. Pattern Recognit. Workshop on Syntactic and Struct. Pattern Recognit (1990) pp. 231–248Google Scholar
  40. 16.40
    B. Coüasnon: Formalisation grammaticale de la connaissance a priori pour l’analyse de documents: Application aux partitions d’orchestre. In: Actes du dixième congrès Reconnaissance des Formes et Intelligence Artificielle, Rennes (1996) pp. 465–474Google Scholar
  41. 16.41
    I. Knopke, D. Byrd: Towards musicdiff: A foundation for improved optical music recognition using multiple recognizers. In: 8th Int. Conf. Music Inf. Retr. (ISMIR) (2007) pp. 123–126Google Scholar
  42. 16.42
    E.P. Bugge, K.L. Juncher, B.S. Mathiesen, J.G. Simonsen: Using sequence alignment and voting to improve optical music recognition from multiple recognizers. In: 12th Int. Soc. Music Inf. Retr. Conf. (ISMIR) (2011) pp. 405–410Google Scholar
  43. 16.43
    M. Church, M.S. Cuthbert: Improving rhythmic transcriptions via probability models applied post-OMR. In: 15th Int. Soc. Music Inf. Retr. Conf. (ISMIR) (2014) pp. 643–648Google Scholar
  44. 16.44
    H.E. Poole: Music printing. In: Music Printing and Publishing, ed. by D.W. Krummel, S. Sadie (Norton, New York 1990) pp. 3–78Google Scholar
  45. 16.45
    R. Rasch (Ed.): Music Publishing in Europe 1600–1900 Concepts and Issues, Bibliography (Berliner Wissenschafts, Berlin 2005)Google Scholar
  46. 16.46
    F. Rossant, I. Bloch: Robust and adaptive OMR system including Fuzzy modeling, Fusion of musical rules, and possible error detection, EURASIP J. Adv. Signal Process. 2007, 81541 (2007)CrossRefGoogle Scholar
  47. 16.47
    L. Pugin, J.A. Burgoyne, I. Fujinaga: MAP adaptation to improve optical music recognition of early music documents using hidden Markov models. In: 8th Int. Conf. Music Inf. Retr. (ISMIR) (2007) pp. 513–516Google Scholar
  48. 16.48
    E. Selfridge-Field: Beyond MIDI: The Handbook of Musical Codes (MIT Press, Cambridge 1997)Google Scholar
  49. 16.49
    Makemusic Inc.: musicXML, (2017)
  50. 16.50
    WG_1599 – Working Group for XML Musical Application: 1599-2008 – IEEE Recommended Practice for Defining a Commonly Acceptable Musical Application Using XML, (2017)
  51. 16.51
    Music Encoding Initiative:
  52. 16.52
    A. Hankinson, P. Roland, I. Fujinaga: The music encoding initiative as a document-encoding framework. In: 12th Int. Soc. Music Inf. Retr. Conf. (ISMIR) (2011) pp. 293–298Google Scholar
  53. 16.53
    A. Hankinson, L. Pugin, I. Fujinaga: An interchange format for optical music recognition applications. In: 11th Conf. Int. Soc. Music Inf. Retr. (ISMIR) (2010) pp. 51–56Google Scholar
  54. 16.54
    T.M. Breuel, U. Kaiserslautern: The hOCR microformat for OCR workflow and results. In: Int. Conf. Document Anal. Recognit. (ICDAR) (2007) pp. 1063–1067CrossRefGoogle Scholar
  55. 16.55
    S. George: Evaluation in the visual perception of music. In: Visual Perception of Music Notation: Online and Offline Recognition, ed. by S. George (IRM, Hershey 2004) p. 308CrossRefGoogle Scholar
  56. 16.56
    M. Dawe: About Neuratron, (2015)
  57. 16.57
    capella-software AG: Products, (2017)
  58. 16.58
    Visiv Ltd: User comments, reviews, etc., (2006)
  59. 16.59
    Visiv Ltd: Version History, (2006)
  60. 16.60
  61. 16.61
    Wikipedia: Audiveris, (2017)
  62. 16.62
    Laurent Pugin: Aruspix,
  63. 16.63
    Christoph Dalitz: GAMERA Project,
  64. 16.64
    G. Vigliensoni, J.A. Burgoyne, A. Hankinson, I. Fujinaga: Automatic pitch detection in printed square notation. In: Proc. Int. Soc. Music Inf. Retr. Conf., Miami (2011) pp. 423–428Google Scholar
  65. 16.65
    L. Pugin, J. Hockman, J.A. Burgoyne, I. Fujinaga: Gamera versus Aruspix: Two optical music recognition approaches. In: 9th Int. Conf. Music Inf. Retr. (ISMIR) (2008) pp. 419–424Google Scholar
  66. 16.66
    J. Cardoso, A. Capela, A. Rebelo, C. Guedes: A connected path approach for staff detection on a music score. In: Proc. 15th IEEE Int. Conf. Image Process (2008) pp. 1005–1008Google Scholar
  67. 16.67
    A. Dutta, U. Pal, A. Fornés, J. Lladós: An Efficient Staff Removal Approach from Printed Musical Documents. In: Proc. 2010 20th Int. Conf. Pattern Recognit (2010) pp. 1965–1968Google Scholar
  68. 16.68
    A. Fornés, V.C. Kieu, M. Visani, N. Journet, A. Dutta: The ICDAR/GREC 2013 Music Scores Competition: Staff removal, Lect. Notes Comput. Sci. 8746, 207–220 (2014)CrossRefGoogle Scholar
  69. 16.69
    Laurent Pugin: Verovio,
  70. 16.70
    L. Pugin, R. Zitellini, P. Roland: Verovio: A library for engraving MEI music notation into SVG. In: 15th Int. Conf. Music Inf. Retr. (ISMIR) (2014) pp. 107–112Google Scholar
  71. 16.71
    McGill University: (2016)
  72. 16.72
    A. Hankinson, W. Liu, L. Pugin, I. Fujinaga: Diva: A web-based document image viewer. In: Conf. Theory Prac. Digital Libraries (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2018

Authors and Affiliations

  • Ichiro Fujinaga
    • 1
    Email author
  • Andrew Hankinson
    • 2
  • Laurent Pugin
    • 3
  1. 1.Schulich School of MusicMcGill UniversityMontrealCanada
  2. 2.Bodleian LibrariesUniversity of OxfordOxfordUK
  3. 3.Swiss RISM OfficeBernSwitzerland

Personalised recommendations