Hervé Bitteur

You need **Java 17**. (Java 19 may be OK as well, but has not yet been tested with Audiveris

> help: Plugins not loading. I made the plugins.xml using notepad+ but it's showing error in loading that file. The content of the plugin file is from here https://audiveris.github.io/audiveris/_pages/advanced/plugins/ >...

> It's hardly able to view it, it's not worth trying, i cant manually edit each thing. It's better I can manually transcribe on musescore. I suspect a poor quality...

The "reason" for this mistake is that just one long stem is visible, while in fact there should be two shorter stems, one above the other. When we do have...

Yes, that's the way it works: 1. Retrieve stem seeds 2. Retrieve not too bad heads 3. Retrieve not too bad connections between stem candidates and head candidates 4. Reduce...

Proposal: The engine could build a histogram of lengths of all stem candidates in the whole sheet. Then detect that this stem length is significantly longer than average, and that...

Yes, prompting the user for guidance right before the set is OCR'ed is a good idea. I already put it on the 5.2 features list.

Yes, it was a V4 feature. Perhaps it could be resurrected for v5. I need to check its feasibility because the model is now very different...

My understanding of Tesseract tessedit_char_whitelist is that it applies when you expect ONLY characters from the white list. See this [section](https://github.com/tesseract-ocr/tesseract/wiki/FAQ#how-do-i-recognize-only-digits) of Tesseract doc. By definition of white list vs...

@Aeliffa I just tried your .omr file. I confirm export to say Musescore shows a nearly empty 3rd page. Then, I tried to retranscribe it from scratch, first using `Book...