A Recursive Born Approach to Nonlinear Inverse Scattering
This is an incremental improvement for computational imaging and wave-based sensing applications.
The paper tackled the problem of nonlinear inverse scattering by combining the Iterative Born Approximation with a total variation regularizer, relating it to neural network layers and using backpropagation to estimate object permittivity, resulting in successful recovery where traditional linear methods fail.
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.