Content Aware Music Score Binarization

Image binarization is a common operation in the pre-processing stage in most Optical Music Recognition (OMR) systems. The choice of an appropriate binarization method for handwritten music scores is a difficult problem. Several works have already evaluated the performance of existing binarization processes in diverse applications. However, no goal-directed studies for music sheets documents were carried out. This paper presents a novel binarization method based on the content knowledge of the image. The method only needs the estimation of the staffline thickness and the vertical distance between two stafflines. This information is extracted directly from the grey level music score. The proposed binarization procedure is experimentally compared with several state of the art methods. An objective evaluation over a large dataset of handwritten music scores is conducted based in the performance of the subsequent steps in an OMR system.