Perform OCR for documents
Before you can test classification, extraction, separation, or any other class-related aspects of your project, it is necessary to run Optical Character Recognition (OCR or recognition) for some test documents. You can select and perform recognition for one or more documents in both the List View and the Hierarchy View. For the best results, add a document set that contains several documents suitable for testing.
You can perform recognition for one or more documents by following these steps:
- Open the Documents window if it is not already open.
-
Select the document set and document subset that you are testing.
The documents in the selected document subset are displayed in the selected view.
-
As needed,
switch to the
List View
or the Hierarchy View
.
If you are testing document separation, use the Hierarchy View. Otherwise, use the List View.
The selected document set is displayed.
-
In the list of documents, select one or more documents that require recognition.
Tip To save time selecting individual documents, click Select All
or Ctrl + A to select all documents.
-
Right-click the selected documents and select
Recognize
.
A submenu is displayed.
-
Select one of the recognition engines listed in the submenu.
A progress window is displayed and closes when the recognition process is finished. Classification can now be performed for the documents that have recognition results.