News for hackers. Stuff that matters.
Re:Using Tesseract OCR with Python by pgodzin on Tuesday July 11, 2017 @12:59AM (#14741676)
Is there a way to combine the character-level OCR with knowledge of the English dictionary? Something like `pregrarrmung` should be able to map to 'programming' especially with n-gram context of pregrarrmung experience.
Re:Using Tesseract OCR with Python by ageitgey on Tuesday July 11, 2017 @01:18AM (#14741739)
Yep, it's called adding a language model.

Check out this paper (2011) for a good summary of the pros and cons: https://research.google.com/pubs/pub36984.html

Re:Using Tesseract OCR with Python by pgodzin on Wednesday July 12, 2017 @02:45AM (#14750614)
This is great, thanks! I wonder how it would do with a more state-of-the-art NN model rather than relying on word frequency as a model.