The second NIST database of structured forms consists of 5,595 pages of binary, black-and-white images of synthesized documents containing hand-print.
The documents in this database are 12 different tax forms with the IRS 1040 Package X for the year 1988. These include Forms 1040, 2106, 2441, 4562, and 6251 together with Schedules A, B, C, D, E, F, and SE. Eight of these forms contain two pages or form faces; therefore, there are 20 different form faces represented in the database.
The document images in this database appear to be real hand-printed forms prepared by individuals, but the images have been automatically derived and synthesized using a computer and contain no "real" tax data. There are 900 simulated tax submissions represented in the database averaging 6.22 form faces per submission.
The database has the following features:
900 simulated tax submissions
5,595 images of completed structured form faces containing hand-printed data
5,595 text files containing entry field answers
20 tables of entry field types and contexts
Suitable for both document processing and automated data capture research, development and evaluation, the database can be used for:
forms identification
field isolation: locating entry fields on the form
character segmentation: separating entry field values into characters
character recognition: identifying specific handprinted characters.
The database is a valuable tool for measurement of system performance and system comparison on complex forms.