Many researchers in Optical Music Recognition have proposed staff removal algorithms in order to make easier the segmentation and enhance the accuracy of music symbol recognition. However, the staff removal task cannot be considered as a solved problem, especially when dealing with ancient/degraded handwritten music scores.

In ICDAR 2011, we organized the first edition of the music scores competition. Since the competition attracted the interest of researchers, we would like to foster this interest by organizing a second edition of this competition in ICDAR 2013.

For this second edition, we have generated new images that emulate typical degradations appearing in old and degraded handwritten documents. In contrast with the 2011 image dataset used in the ICDAR 2011 competition, in this new edition two types of degradations will be considered.

We hope that the new set of images will be challenging for the community.



More Information:

  • M.Visani, V.C.Kieu, A.Fornés, N.Journet. “The ICDAR 2013 Music Scores Competition: Staff Removal”. In 12th International Conference on Document Analysis and Recognition (ICDAR), pp.1439-1443, 2013
  • A.Fornés, V.C.Kieu, M.Visani, N.Journet, A.Dutta. “The ICDAR/GREC 2013 Music Scores Competition: Staff Removal”, in “Graphics Recognition. Current Trends and Challenges”, Lecture Notes in Computer Science, vol. 8746. B.Lamiroy and J.-M. Ogier (Eds.), Springer, Heidelberg, (2014).