CVC-MUSCIMA: a ground truth of handwritten music score images for writer identification and staff removal

@article{Forns2011CVCMUSCIMAAG,
  title={CVC-MUSCIMA: a ground truth of handwritten music score images for writer identification and staff removal},
  author={Alicia Forn{\'e}s and Anjan Dutta and Albert Gordo and Josep Llad{\'o}s},
  journal={International Journal on Document Analysis and Recognition (IJDAR)},
  year={2011},
  volume={15},
  pages={243-251}
}
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… 
The ICDAR 2011 Music Scores Competition: Staff Removal and Writer Identification
TLDR
The goal has been to foster the interest in the analysis of handwritten music scores by the proposal of two different competitions: Staff removal and Writer Identification, which have been tested on the CVC-MUSCIMA database: a ground-truth of handwrittenMusic score images.
The 2012 Music Scores Competitions: Staff Removal and Writer Identification
TLDR
This paper is focused on the proposed new experiment for an extended music competition, describing the new set of images and analyzing the new results.
Towards the Recognition of Compound Music Notes in Handwritten Music Scores
TLDR
This work proposes a method based on perceptual grouping for the recognition of compound music notes and has been tested using several handwritten music scores of the CVC-MUSCIMA database and compared with a commercial Optical Music Recognition software.
Writer identification in handwritten musical scores with bags of notes
TLDR
This work adapts the Bag of Visual Words framework to the task of writer identification in handwritten musical scores and analyzes the effect of two improvements of the representation: a Bhattacharyya embedding, which improves the results at virtually no extra cost, and a Fisher Vector representation that very significantly improves the Results at the cost of a more complex and costly representation.
In Search of a Dataset for Handwritten Optical Music Recognition: Introducing MUSCIMA++
TLDR
The MUSCIMA++ dataset of handwritten music notation is designed that addresses musical symbol recognition and notation reconstruction and allows training and evaluating models for symbol classification, symbol localization, and notation graph assembly, both in isolation and jointly.
A morphological method for music score staff removal
  • T. Géraud
  • Computer Science
    2014 IEEE International Conference on Image Processing (ICIP)
  • 2014
TLDR
The main characteristics of this method is that it essentially relies on mathematical morphology filtering, so it is simple, fast, and its full source code is provided to favor reproducible research.
Handwritten Music Object Detection: Open Issues and Baseline Results
TLDR
This work proposes an end-to-end trainable object detector for music symbols that is capable of detecting almost the full vocabulary of modern music notation in handwritten music scores and shows that a machine learning approach can be used to accurately detect music objects with a mean average precision of over 80%.
Handwritten Historical Music Recognition by Sequence-to-Sequence with Attention Mechanism
TLDR
This paper explores 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 and demonstrates that the approach is promising, especially when compared with long short-term memory neural networks.
Music staffline removal using Convolutional Neural Network
TLDR
This work proposes a staffline removal method using CNN to evaluate window size and mask size retaining the symbol information with improved accuracy and proposes to model the problem as a supervised learning classification task.
Recognition of handwritten music scores
The recognition of handwritten music scores still remains an open problem. The existing approaches can only deal with very simple handwritten scores mainly because of the variability in the
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 49 REFERENCES
Building a system for writer identification on handwritten music scores
17th and 18th century music scores were copied and distributed in a manual way. Music historians are interested in how the compositions were distributed or in other words, who copied the compositions
A Symbol-Dependent Writer Identification Approach in Old Handwritten Music Scores
  • A. Fornés, J. Lladós
  • Computer Science
    2010 12th International Conference on Frontiers in Handwriting Recognition
  • 2010
TLDR
A symbol-dependent approach for identifying the writer of old music scores is introduced, which is based on two symbol recognition methods, to use the Blurred Shape Model descriptor and a DTW-based method for detecting, recognizing and describing the music clefs and notes.
A combination of features for symbol-independent writer identification in old music scores
TLDR
The proposed method has been tested on a database of old music scores from the seventeenth to nineteenth centuries, achieving a recognition rate of about 92% with 20 writers.
A bag of notes approach to writer identification in old handwritten musical scores
TLDR
This paper presents a robust approach for writer identification in a particular kind of graphical documents, old music scores, that adapts the bag of visual terms method for coping with graphic documents.
New methodologies towards an automatic optical recognition of handwritten musical scores
TLDR
A new methodology is presented where elastic matching is used in conjunction with several classi ers, for instance neural networks and hidden Markov models, and it is expected that the obtained results outperform the actual state of the art.
An Efficient Staff Removal Approach from Printed Musical Documents
TLDR
In the proposed methodology, a staffline segment is considered as a horizontal linkage of vertical black runs with uniform height to validate it as a true segment.
Optical recognition of music symbols
TLDR
A comparative study of several recognition algorithms of music symbols using both real and synthetic scores to introduce invariances in the prediction with respect to the known variability in the symbols, particularly relevant on handwritten works.
MusicHand : A Handwritten Music Recognition System
Current methods of digitizing handwritten music for typesetting remain far from ideal despite many years for music typesetting programs to mature. There are essentially two categories of programs in
Knowledge-Based Scribe Recognition in Historical Music Archives
TLDR
The basic formalisms and heuristics for the representation of handwriting characteristics are introduced and the usage of a normalized, weighted Hamming distance function is proposed to calculate the degree of similarity between their handwriting characteristics.
Goal-directed evaluation for the improvement of optical music recognition on early music prints
TLDR
This work uses an adaptive OMR system for early music prints based on hidden Markov models to improve recognition accuracy and presents a goal-directed comparison of several popular adaptive binarization algorithms, which are often evaluated only subjectively.
...
1
2
3
4
5
...