VLSI implementation for real-time extraction of direction vectors from binary images for pattern recognition applications

Author

Cao, J. ; Shridhar, M. ; Ahmadi, M. ; Jullien, G.A.

Author_Institution

Dept. of Electr. Eng., Windsor Univ., Ont., Canada

fYear

1993

fDate

16-18 Aug 1993

Firstpage

963

Abstract

The border direction features of handwritten characters are used in some high accuracy pattern recognition systems. The speed of extracting the direction features in software implementation is generally low in compare with the speed of recognition itself. This paper therefore presents a 1.2 μm CMOS VLSI implementation of directional feature extraction of binary images. The proposed method in this paper offers a potential vehicle to speed up the feature extraction part as well as the entire recognition system

Keywords

CMOS digital integrated circuits; VLSI; character recognition equipment; digital signal processing chips; feature extraction; image recognition; real-time systems; 1.2 micron; CMOS chip; VLSI implementation; binary images; border direction features; direction vectors; directional feature extraction; feature extraction; handwritten characters; pattern recognition applications; real-time extraction; Application software; Artificial neural networks; Character recognition; Feature extraction; Handwriting recognition; Humans; Neural networks; Pattern recognition; Shape; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on

Conference_Location

Detroit, MI

Print_ISBN

0-7803-1760-2

Type

conf

DOI

10.1109/MWSCAS.1993.343230

Filename

343230