Data verification is performed by comparing recognition results with the image of any document part. When the program is not absolutely certain about the accuracy of recognition of a certain characters, it marks them as recognized "unreliably." The purpose of the verification process is to verify such characters and correct any errors if necessary.
ABBYY FlexiCapture SDK offers effective and convenient instruments for checking the validity of captured data and tracking recognition errors:
Recognized data can automatically be checked if needed. This covers simple range checking, comparison with a known value (e.g. supplied as a regular expression or taken from a database), and comparison of data items within one document. Finally, scripts can be used to create very sophisticated checking rules.
Rules could be easily managed with a separate tool – ABBYY FlexiCapture product that is supplied with ABBYY FlexiCapture SDK to set up Document Definitions. This makes solution maintenance at production stage easier since only Document Definition have to be changed, without touching any line of the code.
Nevertheless if developers prefer the rules to be managed via code this is easily configurable using the product API.
Group verification is a verification mode where uncertain recognized characters of the same type are displayed in one group, regardless of their location (they can be even located on different pages of the same document). Developers typically display them in a verifier screen, enabling the operator to easily identify and correct characters that deviate from the group.
Context verification is a verification mode intended for effective verification of uncertain recognized characters of different types within a specific field (“context”). The context verification mode can also be used in order to display fields whose range of values is known or can be easily identified. An example of such a field is a field containing a country or city name.