GSoC 2018: Machine Learning Dataset for OMR - Week 5

Heya! :D
Week 5th is over by now and we are at a good pace with the project. Currently, I think our Implementation part is almost done but we need to heavily test the outputs so that we can be surer for each and everything and make minor changes if required. I and Lasconic are constantly in touch with Herve to understand what is required, how it is to be presented in the XML and other pieces of information from our Application that can help better Audiveris. Coming to this weeks analysis:

Below is the segmented status of the project:

Current status of the project
We are done with:
1. Porting the OMR work from imeta to master.
2. Grace Notes Implementation for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/27
3. Bracket Implementation for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/26
4. Tuplet Implementation for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/22
5. Time Signature Upper and Lower Halves annotation for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/28
6. Rest Dot Implementation for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/23
7. Simple Image URL for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/30
8. Staccato Dot for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/25
9. SMuFL symbols identifier for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/29
10. Repeat dot implementation for OMR tackling the issue: https://github.com/Audiveris/omr-dataset-tools/issues/24
11. Crash error rectification while XML generation. - An issue which was faced while testing it on different kind of scores.
12. Testing of scores on Musescore so that they generate XML. The application has been tested on a dataset of 988 scores and it works perfectly.

Added: Tuplet Implementation made better. Current Implementation identifies each kind of tuplets - zero slant, up slant, down slant and all four kinds of Tuplet types supported by Musescore - Number Bracketed Tuplet, Number Unbracketed Tuplet, Ratio Bracketed Tuplet and Ratio Unbracketed Tuplet. I have tested it, it works fine.

Key accomplishments this week
Made the Tuplet Implementation better. More, I had a discussion with Herve regarding some issue which we were having during the Omr dataset tools run but now it's rectified.

Active PR: https://github.com/musescore/MuseScore/pull/3669

Key tasks that stalled
None

Tasks in the upcoming week:
Firstly, Porting this Tuplet Implementation to imeta. Secondly, Work on making the Grace Note implementation better. More testing. Thirdly, Changing names which are exported to the XML so that they are in sync with OMR i.e use the SMuFL names and Accordingly discuss with Herve on adding missing shapes in OmrShape.java file for consistency.

I am really in love with the project. Hope we get to where we want to, on this project :)

Have a Good Day,
Animesh
Github: https://github.com/nasehim7