Data Verification And Document Indexing

The most visible aspect of a capture system is the user interface for verifying recognition results or manually keying index information. A user interface needs to be efficient and flexible enough to handle all the different types of work that you need.

Data Validation - Getting it Right

Since the goal of the capture system is to accurately capture data about a document (indexing) or from a document (data entry), it only makes sense that the data is properly validated. A validation - also known as an "edit" - is different from visual verification, where an operator reviews the data. Validation is where the software checks the value of a field:

• With a "lookup" to a database or other computer-based list
• By comparing fields that have dependent values (fieldA plus fieldB equals fieldC?)
• With a range check, such as making sure a document date is within the last three months

When a validation fails, a field can be flagged for verification. And when the verifier is finished, the validation should run again to make sure that the data is now clean - or allow them to override the validation. Learn more about data validation.

Reject/Repair and Data Verification

If you are using OCR or ICR to automate your data entry or document indexing, then be prepared to have a user review the results of recognition. This is called "verification". A good verification system will automatically flag fields that need review. Fields may need it because a validation  has failed, or because the recognition result is uncertain. When a character has been flagged, this is called a "reject." The character is rejected because the recognition engine has assigned a low confidence to its value: maybe it is an "8", but it could also be a "B," for example. The verification user interface must make it easy for a user to make the final determination - by looking at both the original image and the data in one glance - and then quickly move on to the next field. Learn more about data verification.

Single- and Multi-pass Verification

A user will normally have to verify two different types of issues, i.e. both low-confidence characters and fields that fail validation. There are a number of different ways this type of information is displayed. The most efficient in one in which both low-confidence characters and fields that fail validation can be corrected in a single pass. Learn how Datacap's verification works.

Key from Image

Some applications are not right for recognition. Many document-indexing applications involve assigning key index values to a document based on information about a document that may not be readily found with any recognition technology. In that case, displaying the document image on screen, with the fields to fill in, can be the best approach. A key-from-image screen can also show field snippets, when the location of the snippets is known. And since key from image is a fall back strategy when recognition fails, a good verification screen can also serve for key-from-image. Learn how you can use Datacap for fast automated indexing.

back to top | request more information | contact Datacap | site map