|
 |
|
|
|
Tips for Evaluating an OCR System |
|
When evaluating an OCR (optical character recognition) system for your
company’s document production system there are five key factors to consider.
These factors are 1. speed, 2. accuracy, 3. functionality, 4. control,
and 5. price.
1. Speed:
An OCR product must often run in sync with other processes, such as a
scanner or MFP device. You may want to avoid an OCR product that’s
significantly slower than your scanner or MFP is in creating the files
you’ll be OCR-ing. As such, the OCR processing rate may be a crucial factor.
If you can perform the OCR as an after-process and not in real-time then OCR
processing rates will be much less of a factor. Keep in mind that, generally
speaking, there is a speed vs. accuracy tradeoff in OCR, the faster the OCR
system, the less accurate the recognition process.
2. Accuracy
The accuracy of the OCR product may often be the deciding factor in
determining which OCR system is appropriate. Many OCR products let the
user select the desired accuracy level. There are at least two aspects
to OCR accuracy that should be considered in evaluating an OCR system.
One issue is how accurate the recognized text is with respect to the
original document. The 2nd issue to consider is how accurate the page
segmentation or decomposition is. In other words, are column headers,
multi-column text, pictures, and graphs, etc. correctly detected?
3. Functionality:
The 2 aspects of OCR accuracy (above, in 2.) relate directly to how
functional the OCR output is going to be. For example, an OCR system
with very accurate text recognition but poor page decomposition is perfect
in an indexing environment since we just need to find all pages in the database
with given text, and users have the ability to highlight the occurrences of the
text on any page in which it occurs. For archiving in a records management environment,
this is probably the kind of OCR accuracy that is required and accurate page decomposition
(e.g. – multi-column text, column captions, etc.) is not (strictly) required.
4. Control
is an important factor in OCR selection. How does the user control the OCR process?
In particular, does a given OCR system allow for multi-page processing? (Most systems do.)
Does an OCR system support batch control? Does it have a watched folder mode? Can it be
operated from the command line or via an SDK? i.e., how much OCR control is afforded to
the user?
5. Finally, of
course, there is price.OCR systems vary greatly in price, from $99 up to the
$100,000’s. Of course, to some extent you get what you pay for. Price is often
determined by several criteria, including: Is the OCR software out of the box?
Is it for manual use or automated production use? Does it have any unique features
that make it compelling for a certain application? How accurate can the system be
when run in its most accurate mode? These are among the criteria used in determining
OCR pricing.
For more
information on OCR products, visit CVISION online at
www.cvisiontech.com
back
to top
|
|
|
Banking Industry: A Customer Testimonial |
| Documents
drive the banking profession and CVISION Technologies has had a strong presence
within the banking industry for years. The Commonwealth Bank of Australia is one
of Australia’s leading financial institutions with businesses in Australia,
New Zealand, Asia and the United Kingdom. We asked Edward Gallimore why the
Bank chose PdfCompressor.
"We wanted to engage in a program of OCR-ing our document base of approximately
60 million pages - in order to improve our user experience, and allow quick navigation
to parts of documents. After investigating half-a-dozen commercial OCR products in
the marketplace, we quickly identified CVista PdfCompressor as being the preferred
option. PdfCompressor outshone its competitors in a number of ways: PdfCompressor
was the fastest of the products we investigated; it seemed robust and intended for
server side 24x7 operation; PdfCompressor was easy to integrate into our processes
(through a simple command line interface); it preserved rich content in our PDFs;
and the compression features were a bonus for saving on storage and transmission
costs."
— Edward Gallimore Senior Architect, Imaging Commonwealth Bank of Australia
Download
a Free Trial of CVISION PdfCompressor
back
to top
|
|
|
CVISION Announces New European Sales Division |
CVISION proudly announces the inception of a European Sales Division. The
European Sales Division is headed by Susan Bosworth, formerly with 3Com
Corporation and Microsoft Corporation. The focus in Europe will be on value
added dealers and software vendors in order to provide complete solutions for
the European market.
One of the European resellers Susan has visited
recently is Lightspeed Business Solutions from Reading, in the UK.
Lightspeed
is a specialist Document Management bureau based in the United Kingdom. They
became a reseller after discovering the benefits of PdfCompressor for themselves.
Lightspeed has become a successful member of the European sales network.
With a wealth
of experience in Document Management, Lightspeed is well placed to cast a critical
eye over any software they use – and after evaluating all the options, the decision
to use PdfCompressor was an easy one.
Simon Cresswell,
Business Project Manger for Lightspeed comments: "It’s not only PdfCompressor’s ability
to compress and OCR documents so effectively; it’s the bullet proof reliability that is
so important to us. We depend on it every day – and it never lets us down."
You can find out
more about Lightspeed by visiting
www.lighsol.co.uk
If you are interested in contacting Susan about reselling opportunities within Europe, please email Susan at
sbosworth@cvisiontech.com
back
to top
|
|
|
Upcoming Events: CVISION to be Exhibiting at AIIM 2007 |
|
Visit CVISION at AIIM Expo Conference in Boston, Booth #3028
CVISION Technologies will be exhibiting at AIIM Expo on April 17-19, 2007
at the Boston Convention Center. Please stop by and see CVISION at booth #3028.
AIIM Conference & Expo is the largest and most important annual gathering of
information management professionals, featuring an educational program
covering the breadth and depth of enterprise content and information
management issues.
back
to top
|
|
|
CVISION Informational Webinar: The Business Case for Converting Company Documents to PDF, and the Impact of PDF/A. |
|
CVISION will be holding an online Webinar entitled: The Advantages of
Converting your Company Documents to PDF. Topics including accuracy
of the conversion process, compression, web optimization, OCR speed &
accuracy, dbase auto-indexing, and PDF/A will be discussed. For your
convenience, the presentation will be conducted right from your computer
and is free of charge. The Webinar will be held on April 26th at 2:30 PM
EST.
To sign up,
visit our website.
back
to top
|
|
| Technical
Talk |
| The
technical support team within CVISION Technologies continues
to provide strong customer service and solutions to clients.
Here’s a recent, common question they encountered:
Q:
Is it possible to search and index all of my PDF files?
A:
Yes it is. The first order of business is to make sure that all your PDF
files are indeed searchable. Once you know they’re searchable, its time to
index them into your database using a full-text search engine.
There are of course differences in PDF file types. Some PDFs are
electronically generated and naturally searchable. Other PDF files,
such as image PDFs, need to be made searchable via an OCR process.
For image PDFs, the OCR process uses a hidden text layer to encode the
text corresponding to each image page. There are numerous OCR software
packages to make your image PDFs searchable, though accuracy and size of
the resulting PDFs are important factors in selecting the right software
for your company.
Some databases with older search engines may have some trouble indexing
on image PDFs with hidden text. This can often be corrected for by updating
to the latest version of the database and the latest release version of the
search engine.
For
more information and answers regarding CVISION Technical Support,
visit our Support
Blog.
back
to top
|
|
| About
CVISION Technologies |
| CVISION’s
software helps convert PDF, TIFF, and JPEG files into compressed,
web-optimized and text-searchable PDF files. CVISION software
creates the world’s most compressed PDF files equipped
with OCR. Our CVista PdfCompressor will reduce black & white
documents to 1/10th of their size and color documents to 1/100th
of their size. Using 10% of the storage, 10% of the bandwidth,
and 10% of people time waiting to retrieve documents adds up
to big savings.
CVISION
has served the needs of industry leaders in the fields of
Financial Services, Banking, Government, Real Estate, and
Law; we are used by over 100 Fortune 500 Companies. CVISION
PdfCompressor integrates with both
Kofax and EMC Captiva,
and includes CovR, a cover recognition module. If you are
interested in seeing the advantages of CVISION’s software
for yourself, please download our free
30-day evaluation copy.
CVISION
has recently expanded its online store product line. Visit our
online store.
back
to top
|
|
|
|
