Can we use Tesseract OCR in Kodular?

I was making an app which uses OCR heavily but the native OCR component does not support Bengali which i need. So, when searching for which OCR services are best, i stumbled upon something called Tesseract OCR which is backed by Google, Open source and completely free. i am asking if it is possible to download the language libraries from Tesseract and somehow store it in our Kodular app, so that we can perform OCR natively without relying on any third party APIs. If possible please give suggestions/solutions. Thanks in advance.

Hi AJOY,

Have you tried following this guide by :raising_hands:TimAi2:raising_hands:

Yes, I have dig into it, it works but it’s very slow and also, it involves multiple API calls, so, I am scared of Google API’s prices going up. And Tesseract can even work offline when packed natively with app.

Everything is possible :grin:
It would be a nice challenge for an extension developer,
but let’s say there isn’t really an easy way to make this integration :face_with_diagonal_mouth:.

1 Like