An Enhanced Deep Learning Scheme for Electromagnetic Imaging of Uniaxial Objects

This article utilizes artificial intelligence (AI) combined with a modified contrast scheme (MCS) technique to reconstruct microwave imaging of uniaxial objects. The 2-D backscattering problem of uniaxial objects is exposed to the transverse magnetic (TM) and transverse electric (TE) incident waves. The TE polarization problem is more severe than TM. The preliminary distribution of the dielectric constant is computed by using MCS and then compared with the dominant current scheme (DCS). MCS adds a local wave amplification coefficient to rectify the contrast and thus solves the inverse scattering problem (ISP) effectively. Moreover, U-Net is employed to reconstruct the distribution of the dielectric constants of the uniaxial objects. Different noises are added to compare the reconstruction results for MCS and DCS. We also verify the effectiveness of our proposed method by the measurement data provided by the Fresnel Institute. Numerical results show that the reconstruction is almost the same for small dielectric constants for both MCS and DCS. However, MCS overwhelms DCSs for dielectric constant reconstruction when the dielectric constant is large. MCS has successfully reconstructed uniaxial objects for higher dielectric constant distributions with better performance and high precision capability.