TY - JOUR
T1 - A Recursive Born Approach to Nonlinear Inverse Scattering
AU - Kamilov, Ulugbek S.
AU - Liu, Dehong
AU - Mansour, Hassan
AU - Boufounos, Petros T.
N1 - Publisher Copyright:
© 1994-2012 IEEE.
PY - 2016/8
Y1 - 2016/8
N2 - The iterative Born approximation (IBA) is a well-known method for describing waves scattered by semitransparent objects. In this letter, we present a novel nonlinear inverse scattering method that combines IBA with an edge-preserving total variation regularizer. The proposed method is obtained by relating iterations of IBA to layers of an artificial multilayer 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.
AB - The iterative Born approximation (IBA) is a well-known method for describing waves scattered by semitransparent objects. In this letter, we present a novel nonlinear inverse scattering method that combines IBA with an edge-preserving total variation regularizer. The proposed method is obtained by relating iterations of IBA to layers of an artificial multilayer 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.
KW - error backpropagation
KW - Inverse scattering
KW - neural networks
KW - sparse recovery
KW - total variation regularization
UR - https://www.scopus.com/pages/publications/84978997455
U2 - 10.1109/LSP.2016.2579647
DO - 10.1109/LSP.2016.2579647
M3 - Article
AN - SCOPUS:84978997455
SN - 1070-9908
VL - 23
SP - 1052
EP - 1056
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
IS - 8
M1 - 7489012
ER -