ICDAR / GREC 2011 : Music Scores: Writer Identification and Staff Removal

Music Scores: Writer Identification and Staff Removal : ICDAR / GREC 2011

In the last years, there has been a growing interest in the analysis of handwritten music scores. In this context, the focus of interest is two-fold: the recognition of handwritten music scores (Optical Music Recognition), and the identification (or verification) of the authorship of an anonymous music score.

In this sense, our goal is to foster interest in the analysis of handwritten music scores by the proposal of two different competitions :

  1. Writer Identification

    Nowadays, musicologists must work very hard to identify the writer of an unknown manuscript. In fact, they do not only perform a musicological analysis of the composition (melody, harmony, rhythm, etc), but also analyze the handwriting style of the manuscript. In this sense, writer identification can be performed by analyzing the shape of the hand-drawn music symbols (e.g. music notes, clefs, accidentals, rests, etc), because it has been shown that the author's handwriting style that characterizes a piece of text is also present in a graphic document.

  2. Staff Removal

    In the Optical Music Recognition systems, staff removal algorithms have attracted many researchers, since a good detection and removal of the staff lines will allow the correct isolation and segmentation of the musical symbols, and consequently, will ease the correct recognition and classification of the music symbols.

These two competitions are independent, but using the CVC-MUSCIMA database. The participants can freely decide if they would like to participate in the first one, in the second one, or in both.

The constest was hosted by CVC Barcelona.