In my application I want to build one optical character recognition system which can extract characters from image and input it into text file ?

Till now I have used pytesseract and OpenCV for this purpose.

It has worked fine for documents with clear text with black color fonts on white background.

But when I use pytesseract with image of following types of documents then I do not get satisfactory results and get many errors in output text

  1. Document with white texts on black background
  2. Handwritten documents
  3. Document with two columns of texts for example in newspapers
  4. Colored certificates
  5. Document with mathematical formulas
  6. Document with Tables

So please inform me whether there is any library/module in linux which I can use directly for OCR purpose for any type of document or I need to use only OpenCV for Image processing first and then use pytesseract for OCR purpose ?

  • That's a lot of difficult things to ask for... consider splitting into several questions. – Nicolas Raoul Apr 5 at 9:59
  • Hello Nicolas, Thank you very much for your help. I am sorry I do not know how to split above question. Above I want to know, Whether there is any software in Linux which I can use directly to extract text from Image (no matter from which document I have taken it) without any error.? ...once again thank you very much for your help :) – Saurabh Jain Apr 8 at 7:10
  • Is there any software [...] to extract text from image [...] without any error? -> No. Sorry, there is no such software. – Nicolas Raoul Apr 8 at 8:02

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.