If the text is very small, like less than 20/30px, you can try to upscale
it and see if it helps.
Otherwise fine tuning is the only alternative I know of.
If you use https://github.com/OCR-D/ocrd-train it is quite simple once you
have the crops and the corresponding text. I did it a few times and
I meant to write ABBYY FineReader, not Affinity.
Am Samstag, 8. Dezember 2018 14:18:42 UTC+1 schrieb
p1146182017...@googlemail.com:
>
> Hi,
>
> I started using Tesseract 4.0.0 (with LTSM) recently and it works
> amazingly well—much better than Affinity and Nuance that were bundled with
> my Sca
2 matches
Mail list logo
