Home/ Questions/Q 6778597
In Process

The Archive Base Latest Questions

Editorial Team
  • 0
Asked: 2026-05-26T16:17:05+00:00

I was incorporating the OCR in my iPhone app using open source library tesseract.I

  • 0

I was incorporating the OCR in my iPhone app using open source library “tesseract”.I have seen some apps on AppStore doing so. I am just wondering how can I segregate the data that it reads from the card, i.e, how will I distinguish between say FirstName and the LastName or between CompanyName and the person’s name, how will I distinguish whether the number is Phone# or the Fax# etc.

I wish that there are some standard formats of the Business Cards but I feel that would be hard luck to assume so.Any inkling on that would help a lot.

I posted it over here to gather the thoughts of various developers so that I can come up with some good logic (to make it more accurate) to classify the data that we get from the OCR engine.

Share

Leave an answer

You must login to add an answer.

Need An Account,

1 Answer

  1. Editorial Team
    • Create some guesses how the various text pieces could be interpreted and let the user pick the best one. The format should be pretty standard per country (e.g. in English/German/French etc., the first name is 99.9% in front of the last name)
    • If now guess is good enough, the user can assign the fields himself
    • For the firstname/lastname problem, you could maybe consult a local file or web service with common pre-parsed names in the user’s country
    • 0