Previous | Next | (P-PDF) Paper to PDF
Topic: Optimizing OCR Process - GUIDANCE PLEASE!!!
Conf: (P-PDF) Paper to PDF, Msg: 23947
From: Jim
Date: 7/13/2001 07:28 PM
Duff is right - don't photocopy unless you must for your scanner (a DocuImage 620S would chew up onionskin).
Try ScanFix from TMSSequoia, or a comparable product, and use the character-smoothing and character-thinning enhancement features. Make sure your images are deskewed. Doing this image enhancement will improve OCR some, but certainly not to the level achieved by a 1st generation document image.
Jim Rile
James Rile Associates
sales@pdfwebsearch.com
www.pdfwebsearch.com
On 7/12/2001 4:35:00 PM, MDarchiver wrote:
>In the process of creating an
>imaging solution for my
>Center, I have hit a HUGE
>snag...
>
>Approx. 20% of the documents I
>will be archiving are 'onion
>skins' which I intend to
>photocopy. The problem that
>I'm running into is that many
>of the skins are 7 or 8
>generation, causing the
>letters to be fuzzy. This
>fuzz is failing to be
>recognized in the OCR
>process!!!
>
>Using Acrobat Capture 3.01,
>I've tried exporting to PDF as
>Image & Text, Searchable Image
>Exact, as well as Searchable
>Image Compact. The best
>result, with two paragraphs
>identified as text, was with
>the Image & Text option; but
>this is by know means
>acceptable.
>
>What can be done on both
>software & hardware ends to
>optimize the OCR process??
>
>Any help would be greatly
>appreciated.
>
>Thanks,
>
>M. C. Desroches
