Skip to main content
Back to homepage →

Paperless has it's own OCR engine, should I use my Fujitsu's OCR as well? - Knowledgebase / Paperless for Mac OS / OCR - Mariner Software

Paperless has it's own OCR engine, should I use my Fujitsu's OCR as well?

Authors list

Paperless has its own OCR engine, should I use my Fujitsu's OCR as well? My Fujitsu came with ABBYY Fine Reader OCR is there any benefit to enable this and then have Paperless OCR it as well? 

The short answer is that it might be helpful to perform both OCR operations. The longer answer is:

The ScanSnap uses ABBYY fine Reader OCR, the resulting PDF will have be layered Image over text - whereas the Paperless OCR engine is Tesseract, which writes the OCR data to the database but not the PDF itself.

So, document protability would be the reason to do both OCR operations; since the ABBYY OCR is written to the pdf and Paperless writes it into the metadata in the database, but not the pdf itself (yet).

Helpful Unhelpful

33 of 54 people found this page helpful