A Comparative Survey of Image Binarisation Algorithms for Optical Recognition on Degraded Musical Sources

Burgoyne, John Ashley; Pugin, Laurent; Eustace, Greg; Fujinaga, Ichiro (2007). A Comparative Survey of Image Binarisation Algorithms for Optical Recognition on Degraded Musical Sources. In: 8th International Conference on Music Information Retrieval (ISMIR 2007) (pp. 509-512). Austrian Computer Society

Full text not available from this repository. (Request a copy)

Binarisation of greyscale images is a critical step in optical music recognition (OMR) preprocessing. Binarising music documents is particularly challenging because of the
nature of music notation, even more so when the sources are degraded, e.g., with ink bleed-through from the other side of the page. This paper presents a comparative evaluation of 25 binarisation algorithms tested on a set of 100 music pages. A real-world OMR infrastructure for early music (Aruspix) was used to perform an objective, goaldirected evaluation of the algorithms’ performance. Our results differ significantly from the ones obtained in studies on non-music documents, which highlights the importance of developing tools specific to our community.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

06 Faculty of Humanities > Other Institutions > Walter Benjamin Kolleg (WBKolleg)

UniBE Contributor:

Pugin, Laurent Xavier

ISBN:

978-3-85403-218-2

Publisher:

Austrian Computer Society

Language:

English

Submitter:

Laurent Xavier Pugin

Date Deposited:

24 Jun 2021 08:37

Last Modified:

24 Jun 2021 08:37

URI:

https://boris.unibe.ch/id/eprint/153527

Actions (login required)

Edit item Edit item
Provide Feedback