Data recognition is the stage during which you locate the fields that you want to capture and then convert the fields into character-based data.
The data that is obtained from recognition is stored in the page data files that you set up in the document assembly stage.
There are several techniques that you can use to identify pages. The most widely used is fingerprint matching. If you used fingerprint matching for page identification, you most likely used the fingerprint images to define the recognition zones. These zones are the fields that you want to read on each page. If you use full page recognition, you can obtain the field data directly from the full page recognition results. Otherwise, you need to run the recognition engine on each field zone to capture the data.
The other recognition techniques do not use fingerprint zones to locate the field data. Instead, they use text matching or pattern matching to analyze the page and identify the fields.
