I am currently finding the problem that when I apply digitization with document undertanding and I put the uipath ocr, this (ocr) when it passes it to plain text it makes it unstructured, I think that when the ocr is passed, this (ocr), it reads it vertically and not horizontally, so in the case of a table it does not take horizontal data and it takes them unstructured.
Evidences:
someone knows how to tell the ocr to read horizontally and not vertically.
Thanks!
can you show us please the corresponding image? Thanks
Which engine was used?
I used uipath’s ocr engine but I don’t see any property so that when I apply it to a document I can read it horizontally
perfect can you also show the image part on which you do the orc. Thanks
The output of executing this activity is a plain text and it is to which I mean that it gets it unstructured and not as it appears in the pdf, I think or believe that it may be because the OCR internally reads the pdf vertically and not horizontally, therefore it does not Get the information well, so my question is if anyone knows about how to change the way an OCR is read so that it reads horizontally or does not de-structure it
Anil_G
mkankatala
V_Roboto_V
avinashy
Vhierdy_Hafidz
Simon1
SenorChang
Llessur
postwick
sharu_priya