Multi-task Layout Analysis of Handwritten Musical Scores

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.

[1]  Carlos Guedes,et al.  Optical music recognition: state-of-the-art and open issues , 2012, International Journal of Multimedia Information Retrieval.

[2]  Alejandro Héctor Toselli,et al.  Probabilistic Music-Symbol Spotting in Handwritten Scores , 2018, 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[3]  Roger Labahn,et al.  READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents , 2018, 2018 13th IAPR International Workshop on Document Analysis Systems (DAS).

[4]  Alejandro Héctor Toselli,et al.  Handwritten Music Recognition for Mensural Notation: Formulation, Data and Baseline Results , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[5]  Ke Zhang,et al.  Music Document Layout Analysis through Machine Learning and Human Feedback , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[6]  Alejandro Héctor Toselli,et al.  ICDAR2017 Competition on Handwritten Text Recognition on the READ Dataset , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[7]  Lorenzo Quirós,et al.  Multi-Task Handwritten Document Layout Analysis , 2018, ArXiv.

[8]  Alejandro Héctor Toselli Rossi,et al.  From HMMs to RNNs: Computer-Assisted Transcription of a Handwritten Notarial Records Collection , 2018, 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[9]  Ichiro Fujinaga,et al.  Deep Neural Networks for Document Processing of Music Score Images , 2018 .

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Ichiro Fujinaga,et al.  Document Analysis of Music Score Images with Selectional Auto-Encoders , 2018, ISMIR.

[12]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[13]  Alejandro Héctor Toselli,et al.  Sheet Music Statistical Layout Analysis , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[14]  Eric Nichols,et al.  Lyric Extraction and Recognition on Digital Images of Early Music Sources , 2009, ISMIR.