Super-resolution imaging method assisted by a left-handed medium slab based on a neural network.

In this study, a super-resolution imaging method is proposed that combines the physical properties of a left-handed medium (LHM) slab and the mathematical methods of a neural network. Firstly, for the problem of super-resolution information loss in the received scattering field in general scenes, the LHM slab is used to construct a perfect lens to recover the evanescent wave component that carries super-resolution information. Secondly, the compressed sensing (CS) method is applied to image the sparse targets under the LHM environment. However, the perfect focus only occurs in spot or line positions. Therefore, the imaging width of conventional methods is limited and a more powerful mathematical method is needed. Finally, the neural network method is introduced to relax the limitations of target imaging width due to its strong non-linear fitting capability. The simulation results demonstrate that the imaging resolution can reach λ/10 with the assistance of LHM, while the CS method can realize super-resolution imaging of λ/20 based on prior information of spatially sparse targets. In addition, the neural network method proposed in this paper relaxes the limitation of targets, realizing super-resolution imaging of λ/20 for general targets.