Page recognition profiles

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 Tungsten TotalAgility -Synchronization Tool Help for more information.

Add recognition profiles for the following page recognition engines: