How to extract the Text from AADHAR Card

Help Studio
1

Hi,

I want to extract the Name and DoB from the scanned image of Aadhar card in pdf format. I used get text activity and able to extract but the problem is some aadhar cards are shot and some are lengthy ones. So UI couldn’t find error I am getting.

How can we extract the text from different sizes of Aadhar cards.

FYI
MicrosoftTeams-image (8)

Aadhaar_letter_large
Aadhaar_letter_large800×781 283 KB

Regards,

2

@raju_alakuntla

Try indicating both separately…and before extract use check app state

Of if one approach failes use try catch and in catch use the second approach to extract

Not sure though how youa re using get text in scanned pdf

Cheers

3

Hi @raju_alakuntla ,

Is it possible for you to provide us with the extracted text from the Get Text Activity ?

Since it is a scanned document, I believe we will not be able to get the details correctly extracted and it might require Document understanding to be used.

Have you checked the feasibility if the extracted text from Get Text activity with different samples and were they be able to get extracted properly with all details ?

4

You can use UiPath document understanding to extract data from documents/images. In this case, since Aadhar document is always in fixed format you can use a form extractor to get the details back.
Documentation Link : https://docs.uipath.com/document-understanding/automation-cloud/latest/user-guide/introduction

Also you can even give a try using read pdf with ocr activity and use regex to extract details required as it is always in a fixed format.

5

This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.