Pattern Analysis and Applications

, Volume 18, Issue 4, pp 933–943 | Cite as

Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation

  • Jorge Calvo-Zaragoza
  • Isabel Barbancho
  • Lorenzo J. Tardón
  • Ana M. Barbancho
Short Paper


Staff detection and removal is one of the most important issues in optical music recognition (OMR) tasks since common approaches for symbol detection and classification are based on this process. Due to its complexity, staff detection and removal is often inaccurate, leading to a great number of errors in posterior stages. For this reason, a new approach that avoids this stage is proposed in this paper, which is expected to overcome these drawbacks. Our approach is put into practice in a case of study focused on scores written in white mensural notation. Symbol detection is performed by using the vertical projection of the staves. The cross-correlation operator for template matching is used at the classification stage. The goodness of our proposal is shown in an experiment in which our proposal attains an extraction rate of 96 % and a classification rate of 92 %, on average. The results found have reinforced the idea of pursuing a new research line in OMR systems without the need of the removal of staff lines.


Optical music recognition Staff detection and removal Ancient music White mensural notation 



This work has been funded by the Ministerio de Educación, Cultura y Deporte of the Spanish Government under a FPU Fellowship No. AP20120939, by the Ministerio de Economía y Competitividad of the Spanish Government under Project No. TIN2013-48152-C2-1-R and Project No. TIN2013-47276-C6-2-R, by the Consejería de Educación de la Comunidad Valenciana under Project No. PROMETEO/2012/017 and by the Junta de Andalucía under Project No. P11-TIC-7154. This work has been done at Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech. The authors are grateful to the person in charge of the Archivo de la Catedral de Málaga, who allowed the utilization of the data sets used in this work.


  1. 1.
    Bainbridge D, Bell T (2001) The challenge of optical music recognition. Lang Resour Eval 35:95–121Google Scholar
  2. 2.
    Barbancho I, Segura C, Tardon LJ, Barbancho AM (2010) Automatic selection of the region of interest in ancient scores. In: MELECON 2010–2010 15th IEEE Mediterranean Electrotechnical Conference, pp 326–331Google Scholar
  3. 3.
    Bribiesca E (1999) A new chain code. Pattern Recognit 32(2):235–251CrossRefGoogle Scholar
  4. 4.
    Chen YS, Chen FS, Teng CH (2013) An optical music recognition system for skew or inverted musical scores. Int J Pattern Recognit Artif Intell 27(07):1–23Google Scholar
  5. 5.
    Deza MM, Deza E (2009) Encyclopedia of Distances, first edn. Springer, New YorkCrossRefGoogle Scholar
  6. 6.
    Duda RO, Hart PE (1973) Pattern classification and scene analysis, first edn. Wiley, HobokenGoogle Scholar
  7. 7.
    Dutta A, Pal U, Fornes A, Llados J (2010) An efficient staff removal approach from printed musical documents. In: Pattern Recognition (ICPR), 2010 20th International Conference. pp 1965–1968Google Scholar
  8. 8.
    Fornés A, Lladós J, Sánchez G (2005) Staff and graphical primitive segmentation in old handwritten music scores. In: Proceedings of the 2005 conference on Artificial Intelligence Research and Development. IOS Press, Amsterdam, pp 83–90Google Scholar
  9. 9.
    Freeman H (1961) On the encoding of arbitrary geometric configurations. Electr Comput IRE Trans EC 10(2):260–268MathSciNetCrossRefGoogle Scholar
  10. 10.
    Gonzalez RC, Woods RE (2007) Digital Image Processing. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  11. 11.
    Hartigan JA (1975) Clustering algorithms. Wiley, HobokenzbMATHGoogle Scholar
  12. 12.
    Hwang SK, Kim WY (2006) Fast and efficient method for computing art. Image Process IEEE Trans 15(1):112–117CrossRefGoogle Scholar
  13. 13.
    Jelinek F (1998) Statistical methods for speech recognition. The MIT Press, CambridgeGoogle Scholar
  14. 14.
    Levenshtein VI (1966) Binary codes capable of correcting deletions, insertions and reversals. Sov Phys Dokl 10:707MathSciNetGoogle Scholar
  15. 15.
    Lewis JP (1995) Fast template matching. In: Vision Interface. Canadian Image Processing and Pattern Recognition Society, Quebec City, pp 120–123Google Scholar
  16. 16.
    Ng KC, Cooper D, Stefani E, Boyle RD, Bailey N (1999) Embracing the composer: optical recognition of handwritten manuscripts. In: Proceedings of the International Computer Music Conference, BeijingGoogle Scholar
  17. 17.
    Otsu N (January 1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66MathSciNetCrossRefGoogle Scholar
  18. 18.
    Caldas Pinto JR, Vieira P, Ramalho M, Mengucci M, Pina P, Muge F (2000) Ancient music recovery for digital libraries. In: Proceedings of the 4th European Conference on Research and Advanced Technology for Digital Libraries, ECDL ’00. Springer, London, pp 24–34Google Scholar
  19. 19.
    João Rogério Caldas Pinto, Vieira P, João Miguel da Costa Sousa (2003) A new graph-like classification method applied to ancient handwritten musical symbols. IJDAR 6(1):10–22Google Scholar
  20. 20.
    Pizer SM, Johnston RE, Ericksen JP, Yankaskas BC, Muller KE (1990) Contrast-limited adaptive histogram equalization: speed and effectiveness. In: Visualization in Biomedical Computing, 1990, Proceedings of the First Conference, pp 337–345Google Scholar
  21. 21.
    Pruslin D (1966) Automatic recognition of sheet music. Sc.d. dissertation, Massachusetts Institute of TechnologyGoogle Scholar
  22. 22.
    Pugin L (2006) Optical music recognition of early typographic prints using hidden markov models. In: ISMIR, pp 53–56Google Scholar
  23. 23.
    Rebelo A, Fujinaga I, Paszkiewicz F, Marcal ARS, Guedes C, Cardoso JS (2012) Optical music recognition: state-of-the-art and open issues. Int J Multimed Inf Retr 1(3):173–190Google Scholar
  24. 24.
    Sarvaiya JN, Patnaik S, Bombaywala S (2009) Image registration by template matching using normalized cross-correlation. In: Advances in Computing, Control, Telecommunication Technologies, 2009. ACT ’09. International Conference on, pp 819–822Google Scholar
  25. 25.
    Sotoodeh M, Tajeripour F (2012) Staff detection and removal using derivation and connected component analysis. In: Artificial Intelligence and Signal Processing (AISP), 2012 16th CSI International Symposium, pp 054–057Google Scholar
  26. 26.
    Stigler SM (1989) Francis Galton’s account of the invention of correlation. Statistical Sci 4:73–79zbMATHMathSciNetCrossRefGoogle Scholar
  27. 27.
    Su B, Lu S, Pal U, Tan CL (2012) An effective staff detection and removal technique for musical documents. In: Document analysis systems (DAS), 2012 10th IAPR International Workshop, pp 160–164Google Scholar
  28. 28.
    Szwoch M (2005) A robust detector for distorted music staves. In: Gagalowicz A, Philips W (eds) computer analysis of images and patterns, vol 3691, Lecture notes in computer science. Springer, Berlin Heidelberg, pp 701–708CrossRefGoogle Scholar
  29. 29.
    Tardón LJ, Sammartino S, Barbancho I, Gómez V, Oliver A (2009) Optical music recognition for scores written in white mensural notation. J Image Video Process 6Google Scholar
  30. 30.
    Toyama F, Shoji K, Miyamichi J (2006) Symbol recognition of printed piano scores with touching symbols. In: Pattern Recognition, 2006. ICPR 2006. 18th International Conference, vol 2, pp 480–483Google Scholar
  31. 31.
    Trier OD, Taxt T (1995) Evaluation of binarization methods for document images. Pattern Analysis Mach Intell IEEE Trans 17(3):312–315CrossRefGoogle Scholar
  32. 32.
    Wei SD, Lai SH (Nov 2008) Fast template matching based on normalized cross correlation with adaptive multilevel winner update. Image Process IEEE Trans 17(11):2227–2235MathSciNetCrossRefGoogle Scholar
  33. 33.
    Zahn CT, Roskies RZ (March 1972) Fourier descriptors for plane closed curves. IEEE Trans Comput 21(3):269–281zbMATHMathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2014

Authors and Affiliations

  • Jorge Calvo-Zaragoza
    • 1
  • Isabel Barbancho
    • 2
  • Lorenzo J. Tardón
    • 2
  • Ana M. Barbancho
    • 2
  1. 1.Departamento de Lenguajes y Sistemas InformáticosUniversidad de AlicanteAlicanteSpain
  2. 2.Universidad de Málaga, ATIC Research Group, Andalucía Tech, ETSI TelecomunicaciónMálagaSpain

Personalised recommendations