A Novel Technique for Localizing the Scatterer in Inverse Profiling of Two Dimensional Circularly Symmetric Dielectric Scatterers Using Degree of Symmetry and Neural Networks

Abstract

A novel technique for localizing the scatterer in microwave imaging of two-dimensional circularly symmetric dielectric scatterers using degree of symmetry and neural networks is presented. The degree of symmetry for a transmitter position is computed as a function of the difference between the first half and the spatially reflected second half of the measured scattered field vector. A Probabilistic Neural Network (PNN) classifier is trained with the degree of symmetry vectors for the different object configurations. It classifies the degree of symmetry vector of the unknown circularly symmetric scatterer presented to it into one of the classes that indicate the radius and location of the centre of the scatterer. Thus the scatterer is localized in the imaging domain. This not only reduces the degrees of freedom in the inversion for the unknown object, thereby aiding the global convergence of the solution, but also results in a reduction in computation time. The technique has been tested on synthetic data and the results are promising.