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:
Brent Reid <[log in to unmask]>
Reply To:
Records Management Program <[log in to unmask]>
Date:
Wed, 21 Mar 2007 15:02:35 -0400
Content-Type:
text/plain
Parts/Attachments:
text/plain (66 lines)
Qualifier - I am a vendor and a consultant.

As you stated there is a wide range of accuracy depending upon the variables
you listed and others. Therefore I won't comment on percentages.

Instead, I will address your question about how accuracy is validated.

In every project that I have implemented that utilizes OCR and/or ICR, there
is a QA process that follows the scanning where a human reviews the scan and
has the opportunity to type in corrections. This is more important with ICR,
as it often deals with handwritten documents.

The software highlights any questionable characters, so the QA person
doesn't have to read every word.

Most software packages are configurable in terms of how certain the software
needs to be that a character was recognized properly before it is
highlighted for review.

For example, the setting could be that if software is less than 99% certain
that it is correct, then it highlights it for review. Or the threshold could
be set at 85%, in which case more errors would get through.


Hope this helps. If you have more questions - feel free to reply to the list
or contact me off line.

Brent Reid
[log in to unmask]


-----Original Message-----
From: Records Management Program [mailto:[log in to unmask]] On Behalf
Of Alexander Fazekas-Paul
Sent: Wednesday, March 21, 2007 1:58 PM
To: [log in to unmask]
Subject: OCR accuracy statistics

Does anyone have any info or statistics on OCR (Optical Character
Recognition) accuracy. I am looking for vendor neutral information/research
on the topic. 

I understand that there may be variables based on original content, scanned
vs. native electronic files, and on what hardware and software has been
used, etc... 

We are implementing ECM at our organization, and a question has been posed
as to how is accurate OCR is, or how is OCR accuracy validated. 

Thanks in advance for any replies.

Alex Fazekas-Paul
In not so sunny, kinda rainy today San Diego.

 
 
---------------------------------
Be a PS3 game guru.
Get your game face on with the latest PS3 news and previews at Yahoo! Games.

List archives at http://lists.ufl.edu/archives/recmgmt-l.html
Contact [log in to unmask] for assistance

List archives at http://lists.ufl.edu/archives/recmgmt-l.html
Contact [log in to unmask] for assistance

ATOM RSS1 RSS2