OCR can't Extract number

Help Studio
, ,
1

Hi all,

I’m using intelligent OCR to extract a “Total” value from a native PDF file. The vlaue I’m trying to extract is: $126,000.00

image

however it cant seem to extract the actual number “126000.00” any ideas? thanks

2

Can you share the PDF , and did you try Read PDF activity , If PDF is not image

3

DS INVOICE template.pdf (46.3 KB)

Here is the pdf file. I can’t use Read PDF activity because I need Intelligent OCR activities to identify which type of document it is as I have to extract “Total” values from many different document formats

4

@kahoyim

using Mircrosoft OCR i can see that amount is coming

image
image1366×768 59.1 KB

If you are using Relative scrapping then Trescent OCR will work

image
image1366×768 36.7 KB

5

image
image1920×1040 119 KB

This is what I mean here, When I use the Intelligent OCR yes it can identify the $4,500.00 but you can see the actual value is empty (when it should be “4500.00”

6

Did you check followed this doc : https://forum.uipath.com/t/receipt-and-invoice-ai-now-available-in-public-preview/125056`Preformatted text`

7

I never actually knew about this, thank you very much this is helpful