This is my first time working on a OCR application. I have lot of scanned images of English text-book pages like this and I want to build a OCR using DL to extract the text from each image.

Can anyone outline just the approach I need to take to implement it?

There are few questions that I couldn't figure out:

1) How do I need to do it? I mean I don't have any target label (or) annotations (or) bounding box. 2) What will be my target label be here? Do I need target label?

3) Is it possible to do un-supervised learning. If so How?

4) What are CRNN algorithms I need to check out to implement it?

Not looking for any api's (or) libraries (like teserract, vision-api etc..).

  • $\begingroup$ I don‘t understand what your question is. What do you want to predict? Please elaborate $\endgroup$
    – Peter
    Jan 6 '20 at 21:59
  • $\begingroup$ @Peter Sorry for the confusion. I've cleaned up the question. I hope you can understand it now. $\endgroup$
    – user_12
    Jan 7 '20 at 10:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.