Javascript must be enabled for the correct page display

Optical Music Recognition of handwritten scores using structural pattern recognition

Doesburg, T. (2008) Optical Music Recognition of handwritten scores using structural pattern recognition. Bachelor's Thesis, Artificial Intelligence.

[img]
Preview
Text
Bachelor_Thesis_Tom_Doesburg.pdf - Published Version

Download (4MB) | Preview

Abstract

Optical music recognition (OMR) is a form of optical character recognition (OCR). Instead of automatic recognition of text, like OCR, OMR focuses on the recognition of musical scores. Commercial software that performs OMR on machine printed scores already exists and produces great results. When the same software gets handwritten music as input, its performance drops dramatically. In this report we explore the recognition of handwritten musical scores. With the use of connected components, structural- and statistical pattern recognition to deal with the variability of handwritten musical symbols we obtained a total precision of 96.2% and a recall of 85.1%. This article focuses on the structural recognition of the music, while the article of Michiel Bergmans (2008) focuses on the statistical part. Furthermore some issues concerning the use of connected components will be discussed as well as the poor recognition of some symbols.

Item Type: Thesis (Bachelor's Thesis)
Degree programme: Artificial Intelligence
Thesis type: Bachelor's Thesis
Language: English
Date Deposited: 15 Feb 2018 07:45
Last Modified: 15 Feb 2018 07:45
URI: https://fse.studenttheses.ub.rug.nl/id/eprint/9510

Actions (login required)

View Item View Item