A Recursive Born Approach to Nonlinear Inverse Scattering

TL;DR

This paper introduces a new nonlinear inverse scattering method that integrates the Iterative Born Approximation with a total variation regularizer, modeled as a neural network, to improve permittivity recovery in complex scattering scenarios.

Contribution

It develops a novel approach combining IBA with neural network techniques and backpropagation for efficient nonlinear inverse scattering estimation.

Findings

Successfully recovers permittivity in complex scattering scenarios

Outperforms traditional linear inverse scattering methods

Accounts for multiple scattering effects

Abstract

The Iterative Born Approximation (IBA) is a well-known method for describing waves scattered by semi-transparent objects. In this paper, we present a novel nonlinear inverse scattering method that combines IBA with an edge-preserving total variation (TV) regularizer. The proposed method is obtained by relating iterations of IBA to layers of a feedforward neural network and developing a corresponding error backpropagation algorithm for efficiently estimating the permittivity of the object. Simulations illustrate that, by accounting for multiple scattering, the method successfully recovers the permittivity distribution where the traditional linear inverse scattering fails.