Handwritten Historical Music Recognition by Sequence-to-Sequence with Attention Mechanism

Despite decades of research in Optical Music Recognition (OMR), the recognition of old handwritten music scores remains a challenge because of the variabilities in the handwriting styles, paper degradation, lack of standard notation, etc. Therefore, the research in OMR systems adapted to the particu...

ver descrição completa

Detalhes bibliográficos
Autores: Baró Mas, Arnau|||0000-0003-1724-1778, Fornés Bisquerra, Alicia|||0000-0002-9692-5336, Badal Pérez-Alarcón, Carles|||0000-0001-8948-9946
Formato: capítulo de livro
Fecha de publicación:2020
País:España
Recursos:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:325028
Acesso em linha:https://ddd.uab.cat/record/325028
https://dx.doi.org/urn:doi:10.1109/ICFHR2020.2020.00046
Access Level:acceso abierto
Palavra-chave:Optical music recognition
Handwritten music recognition
Document image analysis and recognition
Historical Documents
Deep neural networks
Sequence to Sequence
Descrição
Resumo:Despite decades of research in Optical Music Recognition (OMR), the recognition of old handwritten music scores remains a challenge because of the variabilities in the handwriting styles, paper degradation, lack of standard notation, etc. Therefore, the research in OMR systems adapted to the particularities of old manuscripts is crucial to accelerate the conversion of music scores existing in archives into digital libraries, fostering the dissemination and preservation of our music heritage. In this paper we explore the adaptation of sequence-to-sequence models with attention mechanism (used in translation and handwritten text recognition) and the generation of specific synthetic data for recognizing old music scores. The experimental validation demonstrates that our approach is promising, especially when compared with long short-term memory neural networks.