OCR can extract the values from the PDF

[Gunasuriya_Ravi]

Its possible to extract the values from the pdf file like Resume
Its possible to extract the value like Name,phone Number,Email ID from the resume with OCR model
Any suggestion to achieve this?

[Steve]

OCR will only work reliably with consistently-formatted documents:

help.appsheet.com

Optical Character Recognition (OCR)

Extract information from photos and images

[wenli]

Hello Steve,

I am also interested in this function “if OCR can extract the values from the PDF?”.
Understand that OCR only works with consistently-formatted documents.
In case of the the PDFs are consistently-formatted, can OCR also work with PDF files?
If this is possible, no need to take the picture for PDF, so the OCR can be used in much more cases.

Thanks.

[Rajarshi_Basu]

I have uploaded the pdf files in File format. How to extract information from the files using OCR model.

[Aurelien]

Hi @Rajarshi_Basu

OCR works on images only.

For PDF files reading, you may want to prefer using this feature:

help.appsheet.com

Document processing

Learn about document processing with AppSheet.

This is a different structure though, as you will need to add a “folder as a table”.

[Sara_Bertomeu]

Hi, Difficult to recognize and of course change the field.

I'm working with Invoice and a lot of fields are not the same, and of course the language in Spanish it's so difference to read. 

There is any thing that I can do with that?? Thanks 

[Joseph_Seddik]

Hello Sara,

when you need to maintain certain column names for one reason or another, you can always use the Display Name field in every column to show alternate user-oriented names and languages. 

[julianp]

Anyone knows if there is any workaround to this?
Hope they are working on this feature, adding PDF support to OCR seem the most logical thing to do.

[Sara_Bertomeu]

Waiting news!!! Thanks