Hi all,

I made noises on here a few times some time ago about having
'trained' the Tesseract OCR engine to recognise Ancient Greek to a
reasonable standard. That means that optical character recognition
of Ancient Greek is possible on any platform which Tesseract can run
on, which includes Windows, Mac OSX, Linux, and Android.

The Tesseract project doesn't include a graphical interface, however,
which makes running it a bit challenging. There are various
graphical interfaces available, though, so I wrote some (very
skeletal) instructions on installing Tesseract with a graphical
interface for OCR of Ancient Greek:
https://community.dur.ac.uk/nick.white/grctraining/desktop.html

If people are interested and want to give it a go, let me know how
it goes, or if you have problems following the instructions.

From March I will be working on significantly improving the OCR
quality, and I also hope to make proper install bundles simple
enough to render the above page unnecessary.

But hopefully for now this will prove useful for people.

Nick