In past centuries, before the introduction of printed music scores, compositions were copied by hand. The copies were then passed around and copied further which was the way of spreading a composer's work. Such music pieces were often collected by the nobility and their collections form a valuable source of information and cultural heritage. While the composer of a piece of music is often known, information about who copied the scores where and when is often unavailable. However, this information is important for the work of music historians as they try to re-establish the information lost in time and to register the music scores found in archives. In addition, information about the time and place of creation of a copy of a music piece can also deliver important information on the composer in the case of a piece of unknown origin.
The task of a musicologist is similar to that of a criminologist in terms of using handwritings and other available information. However, in this case the handwritten symbols are music score notations instead of letters of the alphabet. A strict definition of music symbols certainly did not exist in the 17th and 18th century, so that differences in the notation of the same symbol exist between different composers and copyists. Furthermore, just like handwritten characters, handwritten music symbols are produced in a personal manner. Musicologists try to establish the personal characteristics of a speaker in order to link other music scores to the same scribe. Characteristics are, for example, the way in which clefs are drawn or the orientation of note stems. Other information about the place and time of creation can be derived from watermarks in the paper or from the kind of paper itself but the identification of such information is not part of the work presented here.
So far, the task of identifying characteristics of a scribe and of attributing a music score to a certain scribe has been a slow and manual process. Collections found in archives often contain 1,000s of handwritten music sources and usually information about the composer and the way of distribution is only available for a small number of these. Establishing the missing information manually is often beyond the available means and also risks further deterioration of the scores. As many libraries are in the process of digitising these scores and making them available online, so that they do not need to be touched frequently by hand anymore, an excellent opportunity arises to (partly) automate the work of musicologists.
The aim of the image analysis subproject at the Fraunhofer Institute for Computer Graphics is to develop ways of characterising a scribe's handwriting and to build a system for musicologists that aids their task by automating the extraction of relevant music symbols, determining the characteristics in these symbols, and then comparing them with other music scores. Optical Music Recognition (OMR) is similar to Optical Character Recognition (OCR) in that it attempts to recognise the information of a digitised piece of paper but in this instance, the symbols to be recognised are music notation symbols, rather than characters. Issues to be solved include the adaption to personal handwriting styles, deteriorated originals, stains, and non-standard symbols. Our approach consists of four steps
1) image preprocessing to segment foreground background,
2) image analysis to identify primitive structures (e.g. lines, circles) of music notation symbols,
3) symbol recognition by combining primitive structures that belong together, and
4) characterising a handwriting style by measuring characteristics of the symbols (e.g. inclination angle of note stems) and classifying them in a feature space.
Each digitised music source receives a feature set at the end of the process, which can then be used in comparative analyses to find music sources that show a similar handwriting style.
Project duration: 01/2003 - 12/2004
Project funding: 130.400 Euro
Dipl.-Inf. René Stahl
Dipl.-Inf. Roland Göcke
eNoteImageAnalyser - Ein Testbed zur Erprobung von Bildverarbeitungsmethoden im Projekt eNoteHistory