Add a page recognition profile

A page recognition profile performs full page recognition. This means that recognition is run against the entire contents of a page. The recognized characters and words along with their physical coordinates on the page are saved to a file called an XDocument (XDoc). This file is later parsed during classification and extraction.

A page recognition profile has a one-to-one relationship with a recognition engine.

If you process PDF documents that have embedded text, recognition is not required and the embedded text is used for extraction. This is only true if the Extended Synchronization Settings are configured to "Import text from PDF files". Otherwise, PDF documents are treated as TIF files and recognition is performed on the entire page. See the Kofax Transformation -Synchronization Tool Help for more information.

You can add a page recognition profile by following these steps:

  1. On the Project tab, in the Configuration group, select Project Settings Project Settings icon.
  2. Select the Recognition tab to view the recognition settings.
  3. Click the Page Profile button.

    A properties window is displayed.

  4. Choose a Page Recognition Method.

    The properties displayed on the window automatically update if you select a different recognition method.

  5. Edit the page recognizer properties and click OK to save your settings and add the new profile.
  6. Optionally, rename the new profile so it has a descriptive name.
  7. Optionally, click OK to close the Project Settings window.
  8. Save the changes to your project.