The recognized leader in OCR

With every new version of a program, marketers try to convince users that revolutionary changes make an upgrade mandatory.

That's a tough sell with a program as mature and refined as ScanSoft Inc.'s OmniPage Pro. Now in Version 11, OmniPage remains the standard in desktop optical character recognition (OCR) software. Bear in mind, however, that although we rate the program highly, it stems primarily from OmniPage's proven track record. The new features in OmniPage Pro 11 will appeal only to a relatively small group of users.

The most touted new feature in OmniPage is its ability to turn PDF files into editable text. All you need to do is right-click on the PDF file in Windows Explorer, choose Convert To and select the format you want.

The program does a good job of recognizing text and simple formats. We were disappointed, however, when we converted complex PDF documents — with many graphic elements and tables—into word processing files. Little of the formatting of the PDF file was retained, and text required a good deal of cleaning up.

OmniPage also goes the other way: As you scan a paper document, it's simple to turn it into a PDF document. In fact, you can turn it into any of four kinds of PDF files: standard PDF, PDF with image substitutes, PDF image on text and PDF image only.

As with the previous versions of OmniPage, the scanning and recognition process is simple to configure and perform. An easy-to-use toolbar makes it a snap to set options for each stage of the process. What's more, OmniPage's ability to perform scheduled and unattended jobs is an attractive option for departments and agencies. With Version 11, ScanSoft claims increases of up to 40 percent in accuracy over the previous version. We're not sure just what that means because we found the earlier version to be about 99 percent accurate in recognizing text. We did find that OmniPage Pro 11 did a somewhat better job of recognizing damaged and degraded faxes than previous versions, which is saying a lot because OmniPage has always been strong in this area.

We also appreciated OmniPage's streamlined correction tools. OmniPage 11 doesn't miss many characters, but even when it does, the new version makes the correction process easier. Once you identify an unrecognized character for the program, OmniPage will automatically correct all instances of that character.

In addition to handling color photo.graphs, OmniPage Pro can now retain color fonts and backgrounds when converting paper documents into digital documents.

We still wish that OmniPage offered more options for scanning images. Color graphics are saved at a resolution of 150 dots per inch, which is a good general-purpose choice. But we'd like to see OmniPage let the user determine the resolution for images. This would allow more flexibility in post-scanning manipulation.

OmniPage's ability to handle tables and spreadsheets also separates it from most of the competition.

Those features, of course, ride on top of one of the best OCR engines available. OmniPage can recognize characters in 114 languages in sizes from 4 points to 72 points. It can even handle multiple languages on the same page and has dictionary support for 18 languages. Even better, the new version is so good at retaining formatting that it no longer requires users to choose between emphasizing the accuracy of text flow and being faithful to the layout of the page and included graphics. Both are reproduced with impressive accuracy.

It was, in fact, OmniPage's OCR engine that was employed by Microsoft Corp. for the built-in OCR capabilities in Office XP. And if you want to use the full-fledged OmniPage Pro 11, you'll find that this more powerful tool integrates seamlessly into Office XP in place of the bundled module.

Unless your department or agency has a special need with respect to PDF files, there's not a lot of incentive to upgrade to OmniPage Pro 11. But if you are working with simple PDF files or you don't already have a desktop OCR tool, OmniPage Pro 11 represents the best in the business.


OmniPage Pro 11

Score: A-

ScanSoft Inc.
(978) 977-2000

Price: OmniPage Pro 11 is available on the General Services Administrationschedule or directly from ScanSoft for $475.

Remarks: OmniPage Pro remains the premier desktop optical character recognitionprogram, but if you already use OmniPage Pro 10, there is not much incentiveto upgrade unless you want to convert documents to and from PDF files.


  • FCW Perspectives
    remote workers (elenabsl/

    Post-pandemic IT leadership

    The rush to maximum telework did more than showcase the importance of IT -- it also forced them to rethink their own operations.

  • Management
    shutterstock image By enzozo; photo ID: 319763930

    Where does the TMF Board go from here?

    With a $1 billion cash infusion, relaxed repayment guidelines and a surge in proposals from federal agencies, questions have been raised about whether the board overseeing the Technology Modernization Fund has been scaled to cope with its newfound popularity.

Stay Connected