A hierarchical system for character recognition

Author

Vlontzos, J.A. ; Kung, S.Y.

Author_Institution

Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA

fYear

1989

Firstpage

1

Abstract

A hierarchical system for character recognition with hidden-Markov model knowledge sources that solves both the context-sensitive problem and the character-instantiation problem is presented. The algorithms and the structure of the system are described, and its operation is discussed. The system achieves 97 to 99% accuracy using a two-level architecture and has been implemented using a systolic array, thus permitting real-time (1 ms per character) multifont and multisize printed character recognition as well as handwriting recognition

Keywords

computerised picture processing; optical character recognition; parallel processing; 1 ms; OCR; accuracy; algorithms; character-instantiation problem; context-sensitive problem; handwriting recognition; hidden-Markov model knowledge sources; hierarchical system for character recognition; multifont printed character recognition; multisize printed character recognition; operation; real-time recognition; systolic array; two-level architecture; Character recognition; Contracts; Handwriting recognition; Hidden Markov models; Hierarchical systems; Parallel processing; Parameter estimation; Real time systems; Speech recognition; Systolic arrays;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1989., IEEE International Symposium on

Conference_Location

Portland, OR

Type

conf

DOI

10.1109/ISCAS.1989.100272

Filename

100272