Machine Vision and Applications

, Volume 28, Issue 5–6, pp 665–674 | Cite as

Staff-line detection and removal using a convolutional neural network

  • Jorge Calvo-Zaragoza
  • Antonio Pertusa
  • Jose Oncina
Short Paper


Staff-line removal is an important preprocessing stage for most optical music recognition systems. Common procedures to solve this task involve image processing techniques. In contrast to these traditional methods based on hand-engineered transformations, the problem can also be approached as a classification task in which each pixel is labeled as either staff or symbol, so that only those that belong to symbols are kept in the image. In order to perform this classification, we propose the use of convolutional neural networks, which have demonstrated an outstanding performance in image retrieval tasks. The initial features of each pixel consist of a square patch from the input image centered at that pixel. The proposed network is trained by using a dataset which contains pairs of scores with and without the staff lines. Our results in both binary and grayscale images show that the proposed technique is very accurate, outperforming both other classifiers and the state-of-the-art strategies considered. In addition, several advantages of the presented methodology with respect to traditional procedures proposed so far are discussed.


Music staff-line removal Optical music recognition Pixel classification Convolutional neural networks 


  1. 1.
    Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010, pp. 177–186. Springer, Berlin (2010)Google Scholar
  2. 2.
    Byrd, D., Simonsen, J.G.: Towards a standard testbed for optical music recognition: definitions, metrics, and page images. J. New Music Res. 44(3), 169–195 (2015)CrossRefGoogle Scholar
  3. 3.
    Calvo-Zaragoza, J., Barbancho, I., Tardón, L.J., Barbancho, A.M.: Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation. Pattern Anal. Appl. 18(4), 933–943 (2015)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Calvo-Zaragoza, J., Micó, L., Oncina, J.: Music staff removal with supervised pixel classification. Int. J. Doc. Anal. Recognit. 19(3), 211–219 (2016)CrossRefGoogle Scholar
  5. 5.
    Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649. IEEE (2012)Google Scholar
  6. 6.
    Dalitz, C., Droettboom, M., Pranzas, B., Fujinaga, I.: A comparative study of staff removal algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 30(5), 753–766 (2008)CrossRefGoogle Scholar
  7. 7.
    Dos Santos Cardoso, J., Capela, A., Rebelo, A., Guedes, C., Pinto da Costa, J.: Staff detection with stable paths. IEEE Trans. Pattern Anal. Mach. Intell. 31(6), 1134–1139 (2009)CrossRefGoogle Scholar
  8. 8.
    Dutta, A., Pal, U., Fornes, A., Llados, J.: An efficient staff removal approach from printed musical documents. In: 2010 20th International Conference on Pattern Recognition (ICPR), pp. 1965–1968 (2010)Google Scholar
  9. 9.
    Fornés, A., Dutta, A., Gordo, A., Lladós, J.: CVC-MUSCIMA: a ground truth of handwritten music score images for writer identification and staff removal. Int. J. Doc. Anal. Recognit. 15(3), 243–251 (2012)CrossRefGoogle Scholar
  10. 10.
    Fornés, A., Kieu, V.C., Visani, M., Journet, N., Dutta, A.: The ICDAR/GREC 2013 music scores competition: staff removal. In: 10th International Workshop on Graphics Recognition, Current Trends and Challenges GREC 2013, Bethlehem, PA, USA, August 20–21, 2013, Revised Selected Papers, pp. 207–220 (2013)Google Scholar
  11. 11.
    Géraud, T.: A morphological method for music score staff removal. In: Proceedings of the 21st International Conference on Image Processing (ICIP), pp. 2599–2603, Paris, France (2014)Google Scholar
  12. 12.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)Google Scholar
  13. 13.
    Hirata, N.S.T.: Multilevel training of binary morphological operators. IEEE Trans. Pattern Anal. Mach. Intell. 31(4), 707–720 (2009)CrossRefGoogle Scholar
  14. 14.
    Kanungo, T., Haralick, R.M., Phillips, I.: Global and local document degradation models. In: Document Analysis and Recognition, 1993, Proceedings of the Second International Conference on, pp. 730–734. IEEE (1993)Google Scholar
  15. 15.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  16. 16.
    dos Santos Montagner, I., Hirata, R., Hirata, N.S.T.: A machine learning based method for staff removal. In: Pattern Recognition (ICPR), 2014 22nd International Conference on, pp. 3162–3167 (2014)Google Scholar
  17. 17.
    Piatkowska, W., Nowak, L., Pawlowski, M., Ogorzalek, M.: Stafflines pattern detection using the swarm intelligence algorithm. In: Bolc, L., Tadeusiewicz, R., Chmielewski, L.J., Wojciechowski, Konrad (eds.) Computer Vision and Graphics. Lecture Notes in Computer Science, vol. 7594, pp. 557–564. Springer, Berlin (2012)Google Scholar
  18. 18.
    Ramirez, C., Ohya, J.: Automatic recognition of square notation symbols in western plainchant manuscripts. J. New Music Res. 43(4), 390–399 (2014)CrossRefGoogle Scholar
  19. 19.
    Rebelo, A., Cardoso, J.S.: Staff line detection and removal in the grayscale domain. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 57–61 (2013)Google Scholar
  20. 20.
    Rebelo, A., Capela, G., Cardoso, J.S.: Optical recognition of music symbols. Int. J. Doc. Anal. Recognit. 13(1), 19–31 (2010)CrossRefGoogle Scholar
  21. 21.
    Rebelo, A., Fujinaga, I., Paszkiewicz, F., Marçal, A.R.S., Guedes, C., Cardoso, J.S.: Optical music recognition: state-of-the-art and open issues. IJMIR 1(3), 173–190 (2012)Google Scholar
  22. 22.
    Rossant, F., Bloch, I.: Robust and adaptive OMR system including fuzzy modeling, fusion of musical rules, and possible error detection. EURASIP J. Appl. Sig. Process. 2007(1), 160–160 (2007)zbMATHGoogle Scholar
  23. 23.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, arXiv:1409.1556 (2014)
  24. 24.
    Su, B., Lu, S., Pal, U., Tan, C.L.: An effective staff detection and removal technique for musical documents. In: 2012 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 160–164 (2012)Google Scholar
  25. 25.
    Tardón, L.J., Sammartino, S., Barbancho, I., Gómez, V., Oliver, A.: Optical music recognition for scores written in white mensural notation. EURASIP. J. Image. Video. Process. 2009, 843401 (2009). doi: 10.1155/2009/843401
  26. 26.
    Typke, R., Wiering, F., Veltkamp, R.C.: A survey of music information retrieval systems. In: ISMIR 2005, 6th International Conference on Music Information Retrieval, London, UK, 11–15 Sept 2005, Proceedings, pp. 153–160 (2005)Google Scholar
  27. 27.
    Visaniy, M., Kieu, V.C., Fornes, A., Journet, N.: ICDAR 2013 music scores competition: staff removal. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1407–1411 (2013)Google Scholar
  28. 28.
    Zeiler, M.D. : ADADELTA: an adaptive learning rate method. CoRR arXiv:1212.5701 (2012)
  29. 29.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Computer Vision—ECCV 2014, pp. 818–833. Springer, Berlin (2014)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Jorge Calvo-Zaragoza
    • 1
  • Antonio Pertusa
    • 1
  • Jose Oncina
    • 1
  1. 1.Department of Software and Computing SystemsUniversity of AlicanteAlicanteSpain

Personalised recommendations