High speed edge detection by sampling a time series with an orthogonal neural network

Author

Ulug, M.E.

Author_Institution

Intelligent Neurons Inc., FL, USA

Volume

4

fYear

1997

fDate

20-25 Apr 1997

Firstpage

3226

Abstract

We introduce a high speed edge detection method where a time series is sampled using an orthogonal neural network, ONN, that is operating in an autoassociative testing mode. The training is done in near real-time. The testing is very fast since there are no calculations involving Gaussian functions, Laplacian operators or convolution. The speed of edge detection is further improved by combining a very simple rule-based expert system with our ONN. A Fourier analysis of an autoassociative ONN is presented. It is also shown that the ONN can improve its performance while on the job using a monitor/teacher system

Keywords

Fourier analysis; Fourier series; edge detection; expert systems; image segmentation; learning (artificial intelligence); neural nets; time series; Fourier analysis; autoassociative testing mode; high speed edge detection; monitor/teacher system; near real-time training; orthogonal neural network; rule-based expert system; sampling; time series; Convolution; Fourier series; Image edge detection; Intelligent networks; Laplace equations; Monitoring; Neural networks; Neurons; Sampling methods; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 1997. Proceedings., 1997 IEEE International Conference on

Conference_Location

Albuquerque, NM

Print_ISBN

0-7803-3612-7

Type

conf

DOI

10.1109/ROBOT.1997.606780

Filename

606780