Title :
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
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;
Conference_Titel :
Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED), 2013 XVIIIth International Seminar/Workshop on
Conference_Location :
Lviv
Print_ISBN :
978-966-02-6765-7
