Audiveris Music Scanner

Audiveris is a complete music scanner going all the way from the scanned music sheet input to the MusicXML output.

Latest informations: 

Note on project hosting:
Audiveris has long been hosted on Java.Net and migrated to Kenai a few months ago. Only the mailing list is still active on Java.Net to keep the set of registered members and provide easy browsing of the existing list archive. Oracle intends to re-implement Java.Net on top of Kenai infrastructure, so one day everything will be back on Java.Net.
For the time being please provide any feedback on users@audiveris.dev.java.net mailing list, in the form of suggestions or bug reports (if possible please attach the scanned image to your report, to help us analyze the program behavior).

Audiveris main window

Project Management

On http://kenai.com/projects/audiveris/ you'll find all related management features (source code, wiki, [mailing list], download area, issue tracking, etc).

Project Goals

Audiveris is an Optical Music Recognition (OMR) module. Starting from the image of a music sheet, it provides high-level logical music information compliant with the MusicXML definition. Other tools such as a Midi Sequencer, or a Composition Editor can then read and update this data.

There are already commercial tools in this area but Audiveris is, to our knowledge, the only open-source OMR tool. It is a cross-platform tool, written in Java, and tested on Windows and Linux. Mac OS would require a volunteer.

Audiveris works with printed music sheets only, the task of recognizing hand-written scores being significantly harder.

Main Features

Input
Input image formats: All major formats: gif, png, tiff, bmp, etc.
Input PDF files: Yes
Direct scanner input: No (Lack of open-source twain interface)

Processing
Support for handwritten scores: No
Number of pages per score: One (Improvement is planned)
Number of staves per system: Any (And can vary between systems)
Number of lines per staff: 5
Support for tablatures: No
Number of voices per measure: Any
Customizable parameters: Yes For detailed tuning via user interface
Integrated learning: Yes To train on specific symbol shapes
User plugins: Yes To allow user extensions

Output
MusicXML file: Yes Using MusicXML version 2.0
Integrated playback: Yes At score level and at measure level
MIDI file: Yes

Foreseen Contributions

Exported MusicXML

Download

Installation

  1. Just extract the distribution zip file in the directory of your choice. The Audiveris main jar file is located in the dist sub-folder.
  2. Run the program:
    • Launch the program by a double-click on the jar file, or use a CLI command such as:
      java -jar <install-dir>/dist/audiveris-3.3.jar
    • You can also use the command line, and run the audiveris.bat file. Doing so, the program is launched with more memory, resulting in much faster processing.

Note: The previous Audiveris version required both the installation of Microsoft C/C++ and the setting of TESSDATA_PREFIX variable for Tesseract OCR. None of these is needed anymore, OCR features work out-of-the-box for Windows and Linux.

Documentation