We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Document Image-Processing System for Name and Address Recognition.
- Authors
Srihari, Sargur N.; Yong-Chul Shin; Ramanaprasad, Vemulapati; Shi, Zhixin
- Abstract
This article describes a real-time document image processing system. Its objective is to recognize names and addresses from scanned address block images extracted from various tax forms of the United States Internal Revenue Service. The Name and Address Block Reader (NABR) system accepts both machine- and hand-printed address block images as input. Salient aspects of the system are presented, including document analysis (connected component analysis, address block extraction, label detection, hand-print/ machine-print discrimination) and document recognition. Document recognition is performed in two nonidentical streams for machineand hand-print; key steps are address parsing, character recognition, word recognition, and postal data base lookup (ZIP+4 and city-stateZIP files). System output is a packet containing the results of recognition together with data base access status file. Real-time throughput (8500 forms/h) is achieved by employing a loosely coupled multi-processing architecture where successive input images are distributed to available address recognition processors. The functional architecture, software design, system architecture, and the hardware implementation are described. Performance evaluation on machine- and hand-written addresses are presented.
- Subjects
IMAGE analysis; IMAGING systems; UNITED States. Bureau of Internal Revenue; ELECTRONIC systems; LABELING-machines; MARKING devices
- Publication
International Journal of Imaging Systems & Technology, 1996, Vol 7, Issue 4, p379
- ISSN
0899-9457
- Publication type
Article
- DOI
10.1002/(SICI)1098-1098(199624)7:4<379::AID-IMA13>3.0.CO;2-R