|
PDF2XL Enterprise Online Help
Table of Contents Concepts OCR - Optical Character Recognition OCR Process
OCR Process
When you open a scanned document, PDF2XL Enterprise will run an OCR process to determine the text from the image of each page. This process will be run whenever you move to a new page (but the results will be kept, so if you navigate to the same page again, PDF2XL Enterprise will load them instead of running the OCR again), and when you convert the document (for any page you have not visited).
The OCR process is very complex, as it should handle many different kinds of scanned documents. In order to allow for such differences, there are some options that can be set by hand to make better use of the OCR engine. Additionally, the OCR process can be helped along by 'teaching' it: providing feedback and corrections of the OCR results while they are being created. This process is called OCR Learning in PDF2XL Enterprise.
The OCR process can also be enhanced by selecting the correct options in the Advanced OCR settings dialog, which is accessible from the Advanced button of the OCR Settings page.
|
|
