Recognition multifrequency microwave images of simple objects behind dielectric wall using neural networks and correlation technique

Author

Drobakhin, O.O. ; Sherstyuk, G.G.

Author_Institution

Oles´ Honchar Dnipropetrovsk Nat. Univ., Dnepropetrovsk, Ukraine

fYear

2013

fDate

23-26 Sept. 2013

Firstpage

133

Lastpage

136

Abstract

Recognition of objects situated behind a dielectric wall has been implemented for real experimental data using neural networks in the form of multilayer perceptron, GRNN, PNN and RBF and correlation techniques. The objects under recognition have been metal parallelepipeds and cylinders with variation of sizes. As the result of the study, it has been found the best settings for the recognition of objects of several geometric shapes.

Keywords

computerised instrumentation; correlation methods; dielectric devices; image recognition; microwave imaging; multilayer perceptrons; object recognition; radial basis function networks; GRNN; PNN; RBF; correlation technique; cylinder; dielectric wall; geometric shape; metal parallelepiped; multilayer perceptron; neural network; object recognition; recognition multifrequency microwave imaging; Apertures; Correlation; Correlation coefficient; Image recognition; Neural networks; Reflection coefficient; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED), 2013 XVIIIth International Seminar/Workshop on

Conference_Location

Lviv

ISSN

2165-3585

Print_ISBN

978-966-02-6765-7

Type

conf

Filename

6653850