Need assistance with a workflow problem. I am attempting to read PDF files that are invoices. The invoices appear scanned and the PDF to Text tool is not accurately identifying records. In the configuration of PDF to Text tool, under "Text Extraction Options" I have Read Text and Image content selected, output options "lines". An example of incorrect reading is it'll read "IO" as "1O" and the invoice number will be incorrect.
Are there other tools/configuration to read scanned PDF's accurately. Due to proprietary information, I cannot provide examples of the invoices.
@schwapa74
as these are scanned invoices there is huge chance of capturing in accurate data
No tool in market guarantees the 100% accuracy of reading data from scanned documents (as per my knowledge)
hope this helps.