Unable to read few rows-document understanding

Hi
I need to read files of PDF and each pdf files has a table(fixed columns and unfixed rows) but it could not fetch some rows correctly even for a single file. I have used form based extractor. Kindly Help.

Thanks in Advance

Hi @KarthikBallary

Is the page classified correctly before to use the form extractor?

Switch to an alternate OCR engine during Digitization and set scale to 2. And then redefine your template table columns.

Hope this helps.

Yes…will attach sceenshot later

I tried with other OCR. but did not change the scale, let me try this

Hi Pls find attached screenshot. Let me know if I am wrong.

OCR tried-Testreact, Microsoft, OminiPage

Hi @KarthikBallary

It seems you have attached screenshots for the keyword based classifier, did you also configure the extractor?

yes attached is keyword based classifier