Extract data from scanned PDFs

[Aishwarya_Bhargava]

i am trying to extract data from some scanned pdfs which have multiple pages and the pages may not have the same orientation.
the type pf pages in the pdfs are like the following images:

Please guide me its really urgent.

[Vrushali_Gave]

@Aishwarya_Bhargava Use Read PDF with OCR activity to read this pdf.

[Aishwarya_Bhargava]

its not giving proper results

[Pradeep_Shiv]

Hello @Aishwarya_Bhargava,

Try using different OCR Activities, and use Matches activity to Extract the Required field!

Cheers

[Aishwarya_Bhargava]

The output is not workable.

[desineediaditya (Aditya D)]

Hi @Aishwarya_Bhargava,

are you able to extract the correct data from Read PDF Text activity?

Regards,
Aditya

[Aishwarya_Bhargava]

no, the characters are not in correct order.

[desineediaditya (Aditya D)]

Hi @Aishwarya_Bhargava,

Then try converting every page in pdf to image and try with UiPath screen ocr.
It was UiPath inhouse OCR. Give it a try
Below is for your reference

- YouTube

Regards,
Aditya