Non-Iterative Methods Based on Dictionary Learning for Inverse Scattering Problems.

In this paper, a non-iterative method based on dictionary learning is proposed to solve inverse scattering problems. The method is inspired by compressed sensing, which indicates that the signal of interest can be decomposed as a linear combination from a set of expansion bases. The bases in our method are obtained by dictionary learning from a set of training data, and they can learn and characterize the intrinsic laws of the interest signal. The performances of the proposed method are verified using simulated data. The proposed dictionary learning-based method is beneficial for inverse scattering problems, and it is able to provide the results fastly within 1 second.