Deep learning based distorted Born iterative method for improving microwave imaging

Abstract

Abstract The distorted Born iterative method (DBIM) is a popular quantitative reconstruction algorithm for solving electromagnetic inverse scattering problems. These problems are non-linear and ill-posed. As a result, the efficiency of the method is limited by local minima. To overcome this, a correct initial guess solution is needed to obtain a satisfactory result. The U-Net based Convolutional Neural Network (CNN) is used in this study to make a good initial guess for the DBIM technique. The permittivity estimate produced at the output of U-Net is then refined using an existing iterative optimization process. This method’s findings are compared with the conventional DBIM approach. Strong scattering profiles of synthetic and experimental datasets with homogeneous and heterogeneous scatterers are investigated to validate the efficiency of the proposed technique. The results suggest that the use of the deep learning technique for an initial guess of DBIM improves accuracy and convergence rate significantly.