Open amitdo opened 8 years ago
You are not 'watching' this repo, so I need to 'call' you... @tfmorris
Thanks for the pointer. I saw that repo and actually attempted to use it since it had a reasonable build process, but, unfortunately, his "port" has made it UTF-8 only while some earlier versions of Tesseract output ISO Latin-1 causing the comparison process to fail with a "bad UTF-8" error.
I just noticed that the issues exported from Google Code include a Makefile and UTF-8 wrapper by Nick White, so I should at least pick up those changes. His repo is at https://gitorious.org/ancient-greek-training-for-tesseract/ocr-evaluation-tools
Check it out: https://github.com/eddieantonio/isri-extended-ascii
https://github.com/eddieantonio/isri-ocr-evaluation-tools/commits/master