Intelligent Word-based Text Recognition

Frank Hönes, Rainer Bleisinger, Andreas Dengel

In: Michael J. W. Chen (Hrsg.). Proceedings of OE'90. High-Speed Inspection Architectures, Barcoding, and Character Recognition September 3 Boston MA United States Seiten 305-316 SPIE 1384 1 SPIE 1991.


The need for making information within paper documents available for computers increases steadily. In this paper we present a system which is capable to read and to simply understand address blocks of business letters. It is based on optical word recognition (OWR) techniques uses feature recognition methods based on word shapes and is largly independent from different fonts and sizes. Even uncertainly recognized words can be identified using a dictionary and a specific verification algorithm. Additionally recognition accuracy is improved considering different knowledge layers like address syntax and logical dictionaries.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence