EasyOCR: Ready-to-use OCR with 40 languages
1–10 of 73 posts
Re: EasyOCR: Ready-to-use OCR with 40 languages
#2What would be the advantage compared to something like Tesseract ?
Re: EasyOCR: Ready-to-use OCR with 40 languages
#3Looking at the Chinese example, it’s kinda funny it managed to output Traditional Chinese characters when the image contains Simplified Chinese; the SC and TC versions look pretty different (园 vs 園, 东 vs 東).
Re: EasyOCR: Ready-to-use OCR with 40 languages
#4What would be the advantage compared to something like Tesseract ?
Tesseract isn't very accurate, especially with text in photos. It works OK for scanned documents, but that's about it.
Re: EasyOCR: Ready-to-use OCR with 40 languages
#5Re: EasyOCR: Ready-to-use OCR with 40 languages
#6What would be the advantage compared to something like Tesseract ?
Tesseract isn't very accurate, especially with text in photos. It works OK for scanned documents, but that's about it.
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.
Re: EasyOCR: Ready-to-use OCR with 40 languages
#7Has anyone tried it? How good is it?
Re: EasyOCR: Ready-to-use OCR with 40 languages
#8Just look at your photo in TikTok and it'll show you ads with your photo already OCR'd
Re: EasyOCR: Ready-to-use OCR with 40 languages
#9Earlier quoted context omitted.
Tesseract isn't very accurate, especially with text in photos. It works OK for scanned documents, but that's about it.
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.
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)