MasterFile's integrated OCR technology makes the content of virtually any image document, such as scanned paper documents into searchable PDF.

 

The Evidence Cruncher -- Powered by the most accurate OCR technology available

In litigation, where the outcome of a case can rest on a single document, OCR accuracy is critical because even small errors in a key word or phrase may prevent that document being found when searching the database and you can't afford to miss documents.

Therefore, the MasterFile Evidence Cruncher uses the most accurate OCR technology available today and we believe that after reviewing the OCR comparisons below, you'll agree you can't do without the Evidence Cruncher's OCR quality in your office. And what's more, it's the most affordable OCR solution integrated with a litigation support tool you'll find.

As no OCR technology is perfect, a few errors may still creep in, even when the scanned document is a clean and clear copy. To deal with these situations, MasterFile provides fuzzy searching which allows for slight differences between your search terms and the text due to OCR errors, spelling, word variations, etc. For example, below, the search term "metallurgy" still matched "metalurgical" despite the misspelling:

 

Compare the accuracy of MasterFile's Evidence Cruncher to OCR results from Adobe and other OCR software

While some use Adobe Acrobat's OCR, its accuracy leaves much to be desired. Here's what PC Magazine said about Adobe Acrobat 9 OCR in their August 2008 issue:

    "Although Adobe Acrobat 9 Pro Extended isn't meant to be an OCR application -- and we'd certainly never recommend it specifically for that use -- it does include a limited capability to do OCR. The feature could use considerable improvement ...

    Acrobat simply refuses to perform OCR on images of old newspaper articles created by many standard online databases widely used in the legal and academic worlds. ...

    The resulting OCR output was dismayingly bad with dozens of the old-newspaper images I tested. In some instances, only one word in twenty came out entirely right."

Below are real world results, from random sample images comparing the OCR quality of MasterFile's Evidence Cruncher against OCR generated by Adobe Acrobat and other OCR software.

Click on a thumbnail to view the full image and the OCR text generated for comparison:

Example 1: Average quality original

Adobe Acrobat 7 -- over 50 errors
MasterFile -- 1 error

 

Example 2: Average quality original

Adobe Acrobat 7 -- over 90 errors
MasterFile -- 10 errors

 

Example 3: Poor quality, two column original

Adobe Acrobat 7 -- incomprehensible
MasterFile -- 19 errors

 

Example 4: Poor quality original

Adobe Acrobat 7 -- over 70 errors
MasterFile -- 20 errors

 

Example 5: Good quality original

Other OCR software -- 15 errors
MasterFile -- no errors

 

If you would like to test the above image samples with your OCR package and see how it compares to MasterFile's Evidence Cruncher, click here to download the original document pages in TIF format.

Click here to review the languages supported by the Evidence Cruncher's OCR module. 

MasterFile Home | Compare MasterFile to CaseMap, Summation, Concordance or Worldox | Contact Us | Site map