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

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.