Treffer: Multi-task Layout Analysis of Handwritten Musical Scores

[EN] Document Layout Analysis (DLA) is a process that must be performed before attempting to recognize the content of handwritten musical scores by a modern automatic or semiautomatic system. DLA should provide the segmentation of the document image into semantically useful region types such as staff, lyrics, etc. In this paper we extend our previous work for DLA of handwritten text documents to also address complex handwritten music scores. This system is able to perform region segmentation, region classification and baseline detection in an integrated manner. Several experiments were performed in two different datasets in order to validate this approach and assess it in different scenarios. Results show high accuracy in such complex manuscripts and very competent computational time, which is a good indicator of the scalability of the method for very large collections. ; This work was partially supported by the Universitat Politecnica de Valencia under grant FPI-420II/899, a 2017-2018 Digital Humanities research grant of the BBVA Foundation for the project Carabela, the History Of Medieval Europe (HOME) project (Ref.: PCI2018-093122) and through the EU project READ (Horizon-2020 program, grant Ref. 674943). NVIDIA Corporation kindly donated the Titan X GPU used for this research. ; Quirós, L.; Toselli, AH.; Vidal, E. (2019). Multi-task Layout Analysis of Handwritten Musical Scores. Springer. 123-134. https://doi.org/10.1007/978-3-030-31321-0_11 ; S ; 123 ; 134 ; Burgoyne, J.A., Ouyang, Y., Himmelman, T., Devaney, J., Pugin, L., Fujinaga, I.: Lyric extraction and recognition on digital images of early music sources. In: Proceedings of the 10th International Society for Music Information Retrieval Conference, vol. 10, pp. 723–727 (2009) ; Calvo-Zaragoza, J., Toselli, A.H., Vidal, E.: Probabilistic music-symbol spotting in handwritten scores. In: 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 558–563, August 2018 ; Calvo-Zaragoza, J., Zhang, K., Saleh, Z., Vigliensoni, G., ...