0
$\begingroup$

I have got medicine wrapper ( Packaging ) of different medicines.

I want to detect medicine name out of it.

I'm using Google Cloud Vision to extract all the text from the medicine wrapper.

Text contains medicine mfg info, address, pin code, expiry date, ingredients and most importantly medicine name.

I want to extract only medicine name out of it.

What are the possible ways to get medicine name ?

Thanks!

$\endgroup$
1
  • $\begingroup$ Be warned: not only the "commercial" name but even the "production name" can differ from country to country. You will want to take that into account $\endgroup$ Jun 3 '20 at 13:00
1
$\begingroup$

The Python Library Python-tesseract is an optical character recognition (OCR) tool for python. That is, it will recognize and “read” the text embedded in images. Python-tesseract is a wrapper for Google's Tesseract-OCR Engin and please tell me where you find the medicine wrapper ( Packaging ) of different medicines.

$\endgroup$
2
  • $\begingroup$ Python-tesseract is a useless library. $\endgroup$ Sep 21 '20 at 11:28
  • $\begingroup$ okay where I can get data $\endgroup$ Sep 21 '20 at 12:05
0
$\begingroup$

If you know the label layer you can isolate this area geometrically or using a marker. If not, try to get a Vademecum (list of medicine names and other characteristics) and after the OCR chose the closest one from it.

$\endgroup$
2
  • $\begingroup$ So do I need to check each and every word with the list of medicine names ? $\endgroup$ Jun 4 '20 at 2:56
  • $\begingroup$ It's a way, yes. You get the text and compare against a list. Alternatively you may find markers, but this will depend on your packaging. The first method is way easier. $\endgroup$ Jun 4 '20 at 20:38

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.