Version 6.0 of PrimeOCR – Brings OCR Software to Large Format

Seattle, WA – Prime Recognition announces that PrimeOCR, version 6.0 has been released and is available immediately as a major upgrade of its production OCR software. The latest release of PrimeOCR provides functionality to recognize large-format pages, recognize rotated text, new auto-zoning and character recognition technology, report text details of existing searchable PDF files, includes sample source code for a REST API implementation, and continued support for the latest release of Windows operating system software, including Windows Server 2012 R2 and Windows Server 2016.

Version 6.0 updates include:

Large Format Image Processing – Large pages, up to 32000 pixels in height and/or width, can now be recognized by PrimeOCR providing capability for customers to be able to index and search large repositories of engineering drawings, oil/gas exploration records, or other large format images. Using a number of licenses of PrimeOCR v6 in parallel, a large major customer has already implemented large image processing into production for a wide range of different sized documents and engineering drawings.

Rotated Text Recognition – Rotated text (in 90 degree increments) on a scanned page can be recognized and included into the OCR output increasing the searchability of repositories. Engineering drawings, as one example,  typically include one or more orientations of rotated text.

Clump Autozoning – A third type of autozoning has been developed to find groupings of text (clumps), which are typically found on engineering drawings, invoices and other unstructured documents.

Improved Image Enhancement – New pre-processing functions (that take place before OCR) include the ability to report the location, orientation and size of lines that are on the page.

Strikethrough Character Recognition –  Strikethrough characters are often found on interim working documents.  Traditionally strikethrough characters are  recognized by OCR software with poor accuracy since the line that runs through each  character causes character segmentation errors.  New technology in version 6 of PrimeOCR can now intelligently remove the connecting segments and report the characters with improved accuracy.

Report Existing Text Attributes from Searchable PDF- PrimeOCR can report many of the text attributes that already exist in a searchable PDF file, including existing searchable text, and the location of that text on the page. PrimeOCR can also identify any text that isn’t already searchable, OCR the text and include the newly recognized text into the PDF output for increased searchability.

Sample Source Code For REST API Implementation – Sample source code is provided to use PrimeOCR through web services for centralized processing. A REST API can be implemented and scanned image files can be submitted to one or more PrimeOCR servers from remote locations or servers through a REST API.

Support for Windows 2012 Server R2, Windows Server 2016 and Windows 10 – PrimeOCR continues to provide high volume OCR conversion with the latest Windows operating systems, including those operating systems running on a virtual machine (VMWare, Hyper-V, and other VMs).

Improved OCR Accuracy through “Voting” Technology

Developed for the production OCR marketplace, PrimeOCR is an “omnifont” Windows™ based software OCR engine and Application Programming Interface (API) toolkit that uses a combination of proprietary “Voting” algorithms and technology licensed from the best retail OCR vendors.

PrimeOCR is able to reduce OCR errors by an average of 65-82% over the best conventional OCR software products while providing much cleaner data by implementing “Voting” technology.  Since manual error correction can account for over 50% of an imaging system cost, by lowering error rates, PrimeOCR can reduce annual operating costs by 35%.

Designed around a fault-tolerant architecture, PrimeOCR provides the production OCR marketplace with a reliable OCR software solution that generates cleaner results than conventional OCR software.

PrimeOCR has won a number of awards, including two “Product of the Year” awards from Imaging Magazine, and a “Top 10 of AIIM.”

Prime Recognition Corporation

Prime Recognition designs and develops advanced optical character recognition, OCR software,  for the production OCR marketplace. Prime Recognition’s goal is to facilitate the acceptance of OCR by reducing errors through the use of sophisticated “Voting” technology.

Prime Recognition worldwide customers include Service Bureaus, System Integrators,  University/Library systems, companies in the Banking, Insurance, Legal, Manufacturing, Medical, and Transportation industries.  However, the largest customer segment is Government, Prime’s largest customer is the U.S. Patent & Trademark, with a number of installations in Defense Department applications, and other government agencies.

Prime Recognition was founded in 1994 and is headquartered in Woodinville, Washington (on Seattle’s “Eastside”, four miles from Microsoft headquarters in Redmond, WA) and can be reached at (425) 895-0550 or To reach Prime Recognition online, visit

PrimeOCR, PrimeView, and PrimeVerify are trademarks of Prime Recognition. Windows is a trademark of Microsoft Corp. All other products are trademarks or registered trademarks of their respective companies.

For additional information contact: