I am trying use the the intelligent ocr activites to extract values from invoices.
However, when I use ‘Digitize Document’ on an xml or htm file, I receive this error:
‘Digitize Document: The extension ‘.xml’ does not have a known content type defined’
is it simply not possible to digitize these formats as of now?
I have used the Microsoft and Abbyy ocr engines, can the engine effect the outcome?