Page identification methods

Fingerprint matching
Fingerprint matching is the method of identifying a page type by using fingerprints. Specifically, a page’s fingerprint is compared to the fingerprints in a database in which each database fingerprint has an associated page type. As a result of fingerprint matching, a page is assigned the page type of the most closely matching database fingerprint.

Structure-based page identification
Structure-based identification uses the position of a page within the batch to determine its type.

Text matching
To complete page identification by using text matching, you must first complete a full page recognition. You can then search the recognition results for a string that is unique to each page type.

IBM Content Classification: Category and rule-based classification
The Datacap CC actions use IBM® Content Classification technology for page type identification in the following interrelated ways: category-based classification and rule-based classification.

Manual page identification
Although many page identification techniques identify pages automatically, you can configure your application to display unrecognized pages to an operator for manual identification.