Re:EasyOCR: Ready-to-use OCR with 40 languages
by albertzeyer on Wednesday July 08, 2020 @08:48AM
(#23769319)
This depends on the model you use, right? As far as I know, Tesseract supports a couple of models, and you could also use a more powerful neural network in there. And if you have trained it well, it should be fine.
[ Parent
| on HN ]
Re:EasyOCR: Ready-to-use OCR with 40 languages
by vmarius on Wednesday July 08, 2020 @09:31AM
(#23769692)
AFAIK Tesseract is trained to recognize characters and uses a bunch of steps to prepare image for recognition. Steps like removing noise, fixing contrast and resizing.
It means that it performs not-so-good when for example image contains black text and white text on green background since this is not "normalized" through image preparation steps and it cannot detect white text on green background (but you can do it yourself)