A SYSTEM TO READ NAMES AND ADDRESSES ON TAX FORMS

The reading of names and addresses is one of the most complex tasks in automated forms processing. This paper describes an integrated real-t ime system to read names and addresses on tax forms of the U.S. Intern al Revenue Service. The Name and Address Block Reader (NABR) system ac cepts both machine-printed and hand-printed address block images as in put. The application software has two major steps: document analysis ( connected component analysis, address block extraction, label detectio n, hand-print/machine-print discrimination) and document recognition. Document recognition has two nonidentical streams for machine-print an d hand-print: the key steps are address parsing, character recognition , weld recognition, and postal database lookup, (ZIP+4 and City-State- ZIP files.) System output is a packet containing the results of recogn ition together with database access status file. Real-time throughput (8500 forms/h) is achieved by employing a loosely coupled multiprocess ing architecture where successive input images are distributed to avai lable address recognition processors. The functional architecture, sof tware design, system architecture, and the hardware implementation are described. Performance evaluation on machine-printed and handwritten addresses are presented.