RECMGMT-L Archives

Records Management

RECMGMT-L@LISTSERV.IGGURU.US

Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Jesse Wilkins <[log in to unmask]>
Reply To:
Records Management Program <[log in to unmask]>
Date:
Wed, 9 Apr 2008 08:11:05 -0600
Content-Type:
text/plain
Parts/Attachments:
text/plain (40 lines)
Fred is of course spot-on (as he usually is) but I would clarify his
clarification. With hand-PRINTED text the OCR engine can be reasonably
accurate depending on how clear the letters are, how bad the printed
characters are, etc.; many of the higher-end engines do pretty well with
constrained handprint (1 character per box, color within the lines please).
With hand-WRITTEN text, e.g. the Palmer Cursive that our third-grade
teachers despaired of ever teaching us, even very good engines just aren't
that good because of the wide array of cursive styles we all use. There are
some niche applications of handwriting recognition in production imaging
environments, including courtesy/legal amount recognition for check
processing, address recognition for the USPS and related firms, and some
others, but it's difficult to get accurate handwriting recognition from e.g.
notes scrawled across a fax cover page. 

Those of you with an exceptional interest in OCR and related recognition and
extraction technologies might check out TAWPI, The Association for Work
Process Improvement, at http://www.tawpi.org. This trade association focuses
pretty specifically on automating paper-centric business processes including
check and remittance processing and mailroom operations, and offers a number
of guidelines on effective use of imaging and extraction technologies. They
do an annual conference and a regional capture conference every year; they
have a certification, the Information Capture Professional or ICP; and their
members routinely process millions of pages or items per month. Not so high
on the archiving or RM side, but very good with regards to processing paper.


Also, AIIM and ARMA both offer some guidance in this area as well - AIIM
probably more than ARMA in my opinion. http://www.aiim.org,
http://www.arma.org. 

Regards, 

Jesse Wilkins
[log in to unmask] 

List archives at http://lists.ufl.edu/archives/recmgmt-l.html
Contact [log in to unmask] for assistance
To unsubscribe from this list, click the below link. If not already present, place UNSUBSCRIBE RECMGMT-L or UNSUB RECMGMT-L in the body of the message.
mailto:[log in to unmask]

ATOM RSS1 RSS2