The Challenge of Optical Music Recognition

This article describes the challenges posed by optical music recognition - a topic in computer science that aims to convert scanned pages of music into an on-line format. First, the problem is described; then a generalised framework for software is presented that emphasises key stages that must be s...

Full description

Saved in:
Bibliographic Details
Published in:Computers and the humanities Vol. 35; no. 2; pp. 95 - 121
Main Authors: Bainbridge, David, Bell, Tim
Format: Journal Article
Language:English
Published: Dordrecht Kluwer Academic Publishers 01.05.2001
Kluwer
Subjects:
Acoustics
Applied sciences
Artificial intelligence
Computer keyboards
Computer music
Computer pattern recognition
Computer science; control theory; systems
Exact sciences and technology
Fundamental areas of phenomenology (including applications)
Image analysis
Music and musical instruments
Music and musical intruments
Musical chords
Musical grammar
Musical notation
Musical staves
Pattern recognition. Digital image processing. Computational geometry
Physics
Staff notation
Partition
Digitizing
Data acquisition system
Pattern recognition
Image processing
Musical acoustics
ISSN:0010-4817, 1572-8412
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article describes the challenges posed by optical music recognition - a topic in computer science that aims to convert scanned pages of music into an on-line format. First, the problem is described; then a generalised framework for software is presented that emphasises key stages that must be solved: staff line identification, musical object location, musical feature classification, and musical semantics. Next, significant research projects in the area are reviewed, showing how each fits the generalised framework. The article concludes by discussing perhaps the most open question in the field: how to compare the accuracy and success of rival systems, highlighting certain steps that help ease the task.
ISSN:0010-4817
1572-8412
DOI:10.1023/A:1002485918032