February 23, 2023, 10:56am
I’m trying a image search workflow example find in doc.
it works but the quality and the précision of the generated text is not perfect.
do you intend to update a new version for tesseract api or there is another solution for OCR ?
other than google vision.
I want an open source solution.
I don’t know of any open source OCR solution with high precision. If I did, i would stop recommening google and aws textract for ocr that needs high precision
February 23, 2023, 12:56pm
Thank you for you reply .
If I understood correctly , for image ocr example you call this api :
GitHub - tesseract-ocr/tessdata: Trained models with support for legacy and LSTM OCR engine with a specific lang.
but when i see this folder in github it’s a 5 years ago (2018) commit version.
Is there a recent or a new tesseract api ?
That is not a question for me, that is question you need to ask the people responsible for that repo
February 23, 2023, 1:44pm
ok , thank you ,
the probleme is that i tried an image ocr workflow with this image
but it give me this response : 8221851
which seems strange to me .
February 23, 2023, 2:19pm
Check this repository (updated):
EasyOCR (python), works for me in some projects a few years ago.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc. - GitHub - JaidedAI/EasyOCR: Ready-to-use OCR with 80+ ...
March 2, 2023, 2:19pm
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.