1. Optical Music Recognition and Data Import/Export Music 253/ CS 275A Eleanor Selfridge-Field

2. 09/02/2010 2 Optical Music Recognition History of efforts from c. 1968 CCARH survey in 1993-4: 37 projects, 7 responses Why is optical recognition difficult? Semantic meaning of many objects depends on graphical context, not purely on shape Sources and their legibility: Manuscripts: very irregular Out-of-copyright prints: images often deteriorated In-copyright prints: not legal to copy Errors in source Biggest problems for OMR developers Superimposition of objects in 2D image Constraints imposed by output formats 2010 Eleanor Selfridge-Field

3. 09/02/20103 Basic problems in optical data acquisition Image is crooked Elements of layout unconventional 2010 Eleanor Selfridge-Field

4. 09/02/20104 How does OMR work? Separation of lines and other matter Isolation of objects Recognition of objects Export to a format for storage, printing, sound, or data interchange Missed: slurs, pedal marks 2010 Eleanor Selfridge-Field

5. 09/02/20105 Why is OMR difficult? Problems of image quality: Ideally Staff lines are straight Spacing is uniform The scanned material is clean (unspotted) Slurs are symmetrical Beams are parallel All lines are unbroken Reality is different! Problems of graphical context Some symbols affect the interpretation of pitch Key signatures Octave alterations   Some symbols affect the interpretation of duration Meter signatures Tempo indicators Fermatas  Some symbols affect dynamics and technique Dynamics marks    Repetition of note-groups , of sections   Instrumental technique    2010 Eleanor Selfridge-Field

6. 09/02/20106 More difficulties Multiple configurations for same objects Methods of evaluation uncertain How to evaluate musical accuracy Handicaps for post-processing Controls for input quality Comparison between different kinds of output Weighing speed against accuracy and usability InputCapture format Post- Processing Carter00:20SCORE9:20 CCARH2:30 + 7:05 MuseData00:15 2010 Eleanor Selfridge-Field

7. 09/02/20107 Close-up views of conventionally typeset music Surface imperfections 2010 Eleanor Selfridge-Field

8. 09/02/20108 Close-up views (2) Missing contextual information Graphic imperfections 2010 Eleanor Selfridge-Field

9. 09/02/20109 Close-up views (3) Dirt Variable presentation of comparable objects 2010 Eleanor Selfridge-Field

10. 09/02/201010 Close-up views (4) Touching objects Conventional presentations 2010 Eleanor Selfridge-Field

11. 09/02/201011 SharpEye: File operations Came from Shetland Islands Source code available Exports to MusicXML Four-step process Capture a page image View the auto-image Correct the image Save/export the result Vis-à-vis MuseData: SE: score-based MD: part-based 2010 Eleanor Selfridge-Field

12. 09/02/201012 SharpEye: Raw Capture 2010 Eleanor Selfridge-Field

13. 09/02/201013 SharpEye: Correcting the interpretation Edit mode: Captured image below Interpreted image above Live object in red Available symbols in red Step 1: Selection a portion the score to edit 2010 Eleanor Selfridge-Field

14. 09/02/201014 SharpEye: Scroll view 2010 Eleanor Selfridge-Field

15. 09/02/201015 SharpEye: System edits 2010 Eleanor Selfridge-Field

16. 09/02/201016 SharpEye: Data-interchange options 2010 Eleanor Selfridge-Field