"A Machine Learning Based Method for Staff Removal"

Igor S. Montagner, Nina S. T. Hirata, Roberto Hirata Jr.

Abstract: Staff line removal is an important pre-processing step to convert content of music score images to machine readable formats. Many heuristic algorithms have been proposed for staff removal and recently a competition was organized in the 2013 ICDAR/GREC conference. Music score images are often subject to different deformations and variations, and existing algorithms do not work well for all cases. We investigate the application of a machine learning based method for the staff removal problem. The method consists in learning multiple image operators from training input-output pairs of images and then combining the results of these operators. Each operator is based on local information provided by a neighborhood window, which is usually manually chosen based on the content of the images. We propose a feature selection based approach for automatically defining the windows and also for combining the operators. The performance of the proposed method is superior to several existing methods and is comparable to the best method in the competition.
All the operators executed in our paper were trained with TRIOSlib. See our guide to learn how to use the operators in this page.
See a comparison between our method and other classic algorithms.

FS operator

The 12 windows below were determined automatically from a set of 70 images from the Training Subset 3.
First level training set Second level training set Trained operator (unzip to use)

BL operator

The following windows were carefuly selected manually for the staff removal task. They can be used as baseline performance for our window selection method.
First level training set Second level training set Trained operator (unzip to use)