Optical Music Recognition: State of the Art and Major Challenges

TL;DR

This paper reviews the current state of Optical Music Recognition, highlighting recent deep learning approaches, challenges in standardization, and proposing future research directions to improve transcription accuracy and evaluation methods.

Contribution

It provides a comprehensive review of OMR methods, discusses challenges in standardization, and offers recommendations for future research to advance the field.

Findings

Deep learning has shifted OMR towards more accurate recognition.

Lack of standardization complicates comparison of methods.

Recommendations for addressing evaluation and pipeline challenges.

Abstract

Optical Music Recognition (OMR) is concerned with transcribing sheet music into a machine-readable format. The transcribed copy should allow musicians to compose, play and edit music by taking a picture of a music sheet. Complete transcription of sheet music would also enable more efficient archival. OMR facilitates examining sheet music statistically or searching for patterns of notations, thus helping use cases in digital musicology too. Recently, there has been a shift in OMR from using conventional computer vision techniques towards a deep learning approach. In this paper, we review relevant works in OMR, including fundamental methods and significant outcomes, and highlight different stages of the OMR pipeline. These stages often lack standard input and output representation and standardised evaluation. Therefore, comparing different approaches and evaluating the impact of different processing methods can become rather complex. This paper provides recommendations for future work, addressing some of the highlighted issues and represents a position in furthering this important field of research.