Recognition of online handwritten music symbols

Abstract

An effective way of digitizing a new musical composition is to use an e-pen and tablet application in which the user's pen strokes are recognized online and the digital score is created with the sole effort of the composition itself. This work aims to be a starting point for research on the recognition of online handwritten music notation. To this end, different alternatives within the two modalities of recognition resulting from this data are presented: online recognition, which uses the strokes marked by a pen, and offline recognition, which uses the image generated after drawing the symbol. A comparative experiment with common machine learning algorithms over a dataset of 3800 samples and 32 different music symbols is presented. Results show that samples of the actual user are needed if good classification rates are pursued. Moreover, algorithms using the online data, on average, achieve better classification results than the others.