The ICDAR/GREC 2013 Music Scores Competition: Staff Removal

Fornés, Alícia; Kieu, van Cuong; Visani, Muriel; Journet, Nicholas; Dutta, Anjan

doi:10.1007/978-3-662-44854-0_16

Cited by 8 publications

(2 citation statements)

References 11 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking advantage of the ICDAR 2013 Competition on Music Scores [10] staff removal contest, we follow its same experimental set-up to assure a fair comparison with other studies and provide reproducible research. This corpus contains pairs of scores with and without staff lines.…”

Section: Methodsmentioning

confidence: 99%

Staff-line detection and removal using a convolutional neural network

Calvo-Zaragoza

Pertusa

Oncina

2017

Machine Vision and Applications

View full text Add to dashboard Cite

Staff-lines 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

show abstract

Section: Methodsmentioning

confidence: 99%

Staff-line detection and removal using a convolutional neural network

Calvo-Zaragoza

Pertusa

Oncina

2017

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…The current performance of staff removal methods can be checked in the GREC/ICDAR 2013 staff removal competition [12,34]. This competition makes use of the CVC-MUSCIMA database [11], which contains handwritten music score images with a perfect ground truth on staff removal.…”

Section: Introductionmentioning

confidence: 99%