0

I have a visiting card contains Name and Adress. those are written in two different languages ( Bengali and English). Now I want to extract the recognized text from the captured image of the visiting card using android or javascript whatever.

Ashik Rabbani
  • 27
  • 7

1 Answers1

0

I've used 'Puthi' previously to decode bengali text(not used professionally, but in a hackathon). Link: https://github.com/afrida67/Puthi-OCR-REST-API

For english I only know about Tesseract https://github.com/rmtheis/tess-two

Hope this helps. :)

All the above libraries are obsolete now,

I think Firebase Ml kit might do the job if you're ok with the limit : https://firebase.google.com/docs/ml-kit/android/recognize-text?authuser=0#before-you-begin

Mohaimanul Chowdhury
  • 111
  • 9
  • thank you @mohaimanul . Probably puthi API is obsoleted. Can you help to use Tesseract in Javascript or android? – Ashik Rabbani Mar 03 '20 at 17:45
  • sorry my bad, I checked further and found out both of these libraries are obsolete now. I think Firebase Ml kit might do the job if you're ok with the limit : https://firebase.google.com/docs/ml-kit/android/recognize-text?authuser=0#before-you-begin – Mohaimanul Chowdhury Mar 03 '20 at 20:35
  • But Firebase ML kit does not support the Bengali Language. – Ashik Rabbani Mar 03 '20 at 20:57
  • this documentation says it does https://firebase.google.com/docs/ml-kit/langid-support But I haven't used it myself so I may be wrong. – Mohaimanul Chowdhury Mar 03 '20 at 21:46