I have academic pdf data. I am using OCR for converting it into text format. The pdf has a few mathematical equations and terms which are acting as noise for my task. Any way through which the task of removing the equations and extracting only the theoretical text data could be automated?

  • $\begingroup$ Please, put your main specific question in the title. Moreover, have you already tried to search on the web for solutions? If yes, describe what you have tried so far. $\endgroup$ – nbro Dec 7 '20 at 11:09
  • $\begingroup$ yes, I did try to look for some solution online but didn't find anything concrete to work with. $\endgroup$ – Gandharv Suri Dec 13 '20 at 9:28
  • $\begingroup$ Could you please edit your post to describe which OCR technique you're using? Could you also provide an example of a pdf that contains such equations and noisy elements? That would probably be a useful context to answer the question more appropriately. $\endgroup$ – nbro Dec 13 '20 at 12:09
  • $\begingroup$ I am using tesseract. The link has an example of the pdf and the converted text file. If you see there are a bunch of locations where there are few mathemtacial equations and symbols like °,®,@, I wanna remove them. drive.google.com/file/d/1BN-dwlCGLk5q_QDsl3r4xryNwjES1J-l/… $\endgroup$ – Gandharv Suri Dec 15 '20 at 7:53
  • $\begingroup$ drive.google.com/drive/folders/… the updated link $\endgroup$ – Gandharv Suri Dec 15 '20 at 8:55

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.