A Trained Regularization Approach Based on Born Iterative Method for Electromagnetic Imaging

A trained-based Born iterative method (TBIM) is developed for electromagnetic imaging (EMI) applications. The proposed TBIM consists of a nested loop; the outer loop executes TBIM iteration steps, while the inner loop executes a trained iterative shrinkage thresholding algorithm (TISTA). The applied TISTA runs linear Landweber iterations implemented with a trained regularization network designed based on U-net architecture. A normalization process was imposed in TISTA that made TISTA training applicable within the proposed TBIM. The iterative utilization of the regularization network in TISTA is a bottleneck that demands high memory allocation through the training process. Therefore TISTA within each TBIM step was trained separately. The TISTA regularization network in each TBIM step was initialized using the weights from the previous TBIM step. The above approach achieved high-quality image restoration after running few TBIM steps while maintained low memory allocation through the training process. The proposed framework can be extended to Newton or quasi-Newton schemes, where within each Newton iteration, a linear ill-posed problem is optimized that differs from one example to another. The numerical results illustrated in this work show the superiority of the proposed TBIM compared to the conventional sparse-based Born iterative method (SBIM).

[1]  Feng Han,et al.  3-D Voxel-Based Reconstruction of Multiple Objects Buried in Layered Media by VBIM Hybridized With Unsupervised Machine Learning , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Rebecca Willett,et al.  Neumann Networks for Linear Inverse Problems in Imaging , 2020, IEEE Transactions on Computational Imaging.

[3]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[4]  Alexandros G. Dimakis,et al.  Deep Learning Techniques for Inverse Problems in Imaging , 2020, IEEE Journal on Selected Areas in Information Theory.

[5]  Qing Huo Liu,et al.  Dual-Module NMM-IEM Machine Learning for Fast Electromagnetic Inversion of Inhomogeneous Scatterers With High Contrasts and Large Electrical Dimensions , 2020, IEEE Transactions on Antennas and Propagation.

[6]  Li Jun Jiang,et al.  Two-Step Enhanced Deep Learning Approach for Electromagnetic Inverse Scattering Problems , 2019, IEEE Antennas and Wireless Propagation Letters.

[7]  Lianlin Li,et al.  DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering , 2018, IEEE Transactions on Antennas and Propagation.

[8]  I. Daubechies,et al.  An iterative thresholding algorithm for linear inverse problems with a sparsity constraint , 2003, math/0307152.

[9]  Krzysztof A. Michalski,et al.  A neural-network approach to the electromagnetic imaging of elliptic conducting cylinders , 2001 .

[10]  Hakan Bagci,et al.  A Preconditioned Inexact Newton Method for Nonlinear Sparse Electromagnetic Imaging , 2015, IEEE Geoscience and Remote Sensing Letters.

[11]  Xudong Chen,et al.  Deep-Learning Schemes for Full-Wave Nonlinear Inverse Scattering Problems , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[12]  H. Bagci,et al.  A Neural Network Assisted Greedy Algorithm For Sparse Electromagnetic Imaging. , 2019, 1911.06514.

[13]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[14]  Hakan Bagci,et al.  Shrinkage-Thresholding Enhanced Born Iterative Method for Solving 2D Inverse Electromagnetic Scattering Problem , 2014, IEEE Transactions on Antennas and Propagation.