OmniPage 18

From DigitWiki
Jump to: navigation, search


OmniPage is a robust optical character recognition (OCR) application available from Nuance Communications. It convers over 120 of languages, including Cyrillic, Chinese, Greek, Japanese and Korean. It is compatible with multiple output formats, including Amazon® Kindle®, PDF, Microsoft® Word, Corel®, HTML and WordPerfect®. It can be used for various purposes, e.g. OCR, ICR, OMR, barcode.

The OmniPage OCR tool is available in four versions, including:

  • Standard version – basic desktop distribution of the OmniPage with most important features of OCR (e.g. language detection, conversion to ebook readers and cloud connectors).
  • Professional version – adds more possibilities in comparison to standard version, e.g. batch processing of watched folders, launchpad or deeper integration with cameras or integration with content management systems (e.g. MS SharePoint).
  • Ultimate version – adds to Professional version DocuDirect solution for batch processing and Sharepoint 2013 integration.
  • SDK version – dedicated version for software developers. It allows adding OmniPage as a build-in OCR engine into software components (e.g. as a part of transcription tool).
  • Cloud Service version – based on cloud technologies OCR engine distribution. Can be used by external applications via dedicated API. It can also be connected to Microsoft Azure.

Please refer to the comparison table of Standard, Professional and Ultimate versions for further details on their differences.

System Requirements

Operating System

In general Windows XP SP3 or newer, but for details please refer to the User’s Guide of adequate version (User’s Guides are listed in the Documentation section of this document)

Hardware Dependencies

Please refer to the User’s Guide of adequate version (User’s Guides are listed in the Documentation section of this document)

Software Dependencies





The trial version of OmniPage Professional 18 for Windows can be obtained at

The trial version of SDK can be obtained at

There is also possibility to use trial version of the Cloud Service. It is available at:

Installation Instructions

OmniPage comes with an installer. For detailed installation instructions please refer to the appropriate User’s Guide. The links to the User’s Guides are listed in the Table 1.

Quick Start Guide

To get started with OmniPage have a look at the sample workflows available in the Process -> Workflows menu. You can see there a list of predefined workflows, which can be used for testing the software.


Configuration and Customization

The User’s Guides are prepared for specific versions of the OmniPage. Please refer to the Table 1 below for appropriate information on where the user guide is located.

Table 1 User's Guides for specific OmniPage versions


Link to the User’s Guide

Standard and Professional



Available after installation in the Start->Programs->Nuance Omnipage Capture SDK 19->Documentation

Cloud Service

The guides provide extensive information regarding the program’s commands and working areas, task-oriented instructions and ways to customize and control processing. In addition to that, in case of window applications, the How-to-Guides available in the Help menu provide concise overviews of key program areas, such as getting input, image improvement, zoning, recognition, editing and proofreading.

Workflow Integration

In case of complex jobs, those can be defined using the OmniPage’s built-in workflow mechanism and then executed either manually on individual files, using a batch manager on large volumes of data, or automatically via watched folders or e-mail accounts. Please consult the Workflows section of the appropriate User’s Guide for detailed information. Please note that full workflow support is provided in Professional and Ultimate versions only.


In order to convert a camera image to a searchable PDF file:

  1. Pick the “Camera Image to Searchable PDF” workflow from the Process -> Workflows menu.

Omnipage Omnipage.png

  1. Start the workflow using the “Start processing” button.
  2. Pick a camera image.
  3. Proofread the results of the OCR and correct if necessary.
  4. Save the PDF file to disk.