TY - JOUR
T1 - CVC-MUSCIMA: A ground truth of handwritten music score images for writer identification and staff removal
AU - Fornés, Alicia
AU - Dutta, Anjan
AU - Gordo, Albert
AU - Lladós, Josep
PY - 2012/9/1
Y1 - 2012/9/1
N2 - The analysis of music scores has been an active research field in the last decades. However, there are no publicly available databases of handwritten music scores for the research community. In this paper, we present the CVC-MUSCIMA database and ground truth of handwritten music score images. The dataset consists of 1,000 music sheets written by 50 different musicians. It has been especially designed for writer identification and staff removal tasks. In addition to the description of the dataset, ground truth, partitioning, and evaluation metrics, we also provide some baseline results for easing the comparison between different approaches. © 2011 Springer-Verlag.
AB - The analysis of music scores has been an active research field in the last decades. However, there are no publicly available databases of handwritten music scores for the research community. In this paper, we present the CVC-MUSCIMA database and ground truth of handwritten music score images. The dataset consists of 1,000 music sheets written by 50 different musicians. It has been especially designed for writer identification and staff removal tasks. In addition to the description of the dataset, ground truth, partitioning, and evaluation metrics, we also provide some baseline results for easing the comparison between different approaches. © 2011 Springer-Verlag.
KW - Graphics recognition
KW - Ground truths
KW - Handwritten documents
KW - Music scores
KW - Performance evaluation
KW - Staff removal
KW - Writer identification
U2 - 10.1007/s10032-011-0168-2
DO - 10.1007/s10032-011-0168-2
M3 - Article
SN - 1433-2833
VL - 15
SP - 243
EP - 251
JO - International Journal on Document Analysis and Recognition
JF - International Journal on Document Analysis and Recognition
IS - 3
ER -