Audiveris
is an open-source Optical Music Recognition
software which processes the image of a music sheet to
automatically provide symbolic music information in
MusicXML standard.
This opens the door to many tools (score editor, MIDI sequencer, ...) which can use this symbolic data for such tasks as edit, play, print, re-publish, transpose, query, etc.
This opens the door to many tools (score editor, MIDI sequencer, ...) which can use this symbolic data for such tasks as edit, play, print, re-publish, transpose, query, etc.
Main features:
- Printed music as input (no handwritten music)
- Standard music notation (no tablatures yet)
- Input formats: PDF, JPG, PNG, TIFF, BMP, ...
- Output format: MusicXML version 2
- Any number of pages per score, of parts per system, of staves per part, of voices per measure
- Internal neural network trainable by end user
- Available on Windows and Linux platforms
- GNU GPL V2 license
News
- Windows installer released
February 22, 2012
- New V4.1beta released
February 1, 2012
- Audiveris at FOSDEM 2012
January 11, 2012
Development
Audiveris is developed in Java, and invokes Google Tesseract OCR (C++) for text recognition.
Project components (source code, binaries, issues tracking, forum) are available on Kenai.
Help wanted for
- Upgrading from Tesseract OCR V2.04 to V3.x
- Coupling with MuseScore to edit, print, play, etc
- Use of cloud computing to provide "OMR as a service"
- Automated evaluation of transcription results
- Microedition features to enable crowd-sourcing approaches