How can I use OCR for an image in PDF

[Anna44]

Hello,

I would like to use OCR for the extraction of  passports, i.e. passport number in a PDF. 

Is this possible in enterprise guide BI 7.1 or enterprise miner client 14.1? And if so, is there a script or manual about how to do this?

Thanks in advance. 

[Kurt_Bremser · Accepted solution]

Use external OCR software to convert the image to text before reading the resulting text into SAS.

SAS does not have in-built OCR, AFAIK.

See hints for using google tesseract from SAS here: https://communities.sas.com/t5/SAS-Text-and-Content-Analytics/How-to-import-pdf-and-jpg-files-in-SAS...