A Recursive Born Approach to Nonlinear Inverse Scattering

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.

Cited by in corpus (11)

• FISTA-Net: Learning A Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging
• High-resolution 3D refractive index microscopy of multiple-scattering samples from intensity images
• Efficient and accurate inversion of multiple scattering with deep learning
• Diffraction tomography with a deep image prior
• Efficient Inversion of Multiple-Scattering Model for Optical Diffraction Tomography
• Holographic particle localization under multiple scattering
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning
• Large-scale holographic particle 3D imaging with the beam propagation model
• Phaseless Microwave Imaging Of Dielectric Cylinders: An Artificial Neural Networks-Based Approach
• Reconstructions of refractive index tomograms via discrete algebraic reconstruction technique
• Fourier synthesis optical diffraction tomography for kilohertz rate volumetric imaging