Deep-Learning Schemes for Full-Wave Nonlinear Inverse Scattering Problems

This paper is devoted to solving a full-wave inverse scattering problem (ISP), which is aimed at retrieving permittivities of dielectric scatterers from the knowledge of measured scattering data. ISPs are highly nonlinear due to multiple scattering, and iterative algorithms with regularizations are often used to solve such problems. However, they are associated with heavy computational cost, and consequently, they are often time-consuming. This paper proposes the convolutional neural network (CNN) technique to solve full-wave ISPs. We introduce and compare three training schemes based on U-Net CNN, including direct inversion, backpropagation, and dominant current schemes (DCS). Several representative tests are carried out, including both synthetic and experimental data, to evaluate the performances of the proposed methods. It is demonstrated that the proposed DCS outperforms the other two schemes in terms of accuracy and is able to solve typical ISPs quickly within 1 s. The proposed deep-learning inversion scheme is promising in providing quantitative images in real time.

[1]  Xudong Chen,et al.  Computational Methods for Electromagnetic Inverse Scattering , 2018 .

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Gaofeng Wang,et al.  A Hybrid Regularization Technique for Solving Highly Nonlinear Inverse Scattering Problems , 2018, IEEE Transactions on Microwave Theory and Techniques.

[4]  Jason Cong,et al.  Minimizing Computation in Convolutional Neural Networks , 2014, ICANN.

[5]  T. Habashy,et al.  Simultaneous nonlinear reconstruction of two‐dimensional permittivity and conductivity , 1994 .

[6]  T. Habashy,et al.  Beyond the Born and Rytov approximations: A nonlinear approach to electromagnetic scattering , 1993 .

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

[8]  R. Kress,et al.  Inverse Acoustic and Electromagnetic Scattering Theory , 1992 .

[9]  Xudong Chen.  Subspace-based optimization method for inverse scattering problems with an inhomogeneous background medium , 2010 .

[10]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[11]  Qing Huo Liu,et al.  Through-wall imaging (TWI) by radar: 2-D tomographic results and analyses , 2005, IEEE Trans. Geosci. Remote. Sens..

[12]  Dacheng Tao,et al.  Non-Local Auto-Encoder With Collaborative Stabilization for Image Restoration , 2016, IEEE Transactions on Image Processing.

[13]  P. Chaumet,et al.  Superresolution in total internal reflection tomography. , 2005, Journal of the Optical Society of America. A, Optics, image science, and vision.

[14]  A. Kirsch.  An Introduction to the Mathematical Theory of Inverse Problems , 1996, Applied Mathematical Sciences.

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

[16]  Ioannis T. Rekanos,et al.  Neural-network-based inverse-scattering technique for online microwave medical imaging , 2002 .

[17]  Xudong Chen,et al.  An FFT Twofold Subspace-Based Optimization Method for Solving Electromagnetic Inverse Scattering Problems , 2011, IEEE Transactions on Antennas and Propagation.

[18]  W. Chew,et al.  Reconstruction of two-dimensional permittivity distribution using the distorted Born iterative method. , 1990, IEEE transactions on medical imaging.

[19]  Horst Bischof,et al.  ATGV-Net: Accurate Depth Super-Resolution , 2016, ECCV.

[20]  C. Eyraud,et al.  Free space experimental scattering database continuation: experimental set-up and measurement precision , 2005 .

[21]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[22]  Alfio Quarteroni,et al.  Complex Systems in Biomedicine , 2006 .

[23]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  R. Mittra,et al.  Computational Methods for Electromagnetics , 1997 .

[25]  P. M. Berg,et al.  Extended contrast source inversion , 1999 .

[26]  Robert E. Kalaba,et al.  System identification: Associate memories for system identification: Inverse problems in remote sensing , 1990 .

[27]  Weng Cho Chew,et al.  An iterative solution of the two‐dimensional electromagnetic inverse scattering problem , 1989, Int. J. Imaging Syst. Technol..

[28]  Paolo Gamba,et al.  Electromagnetic detection of dielectric cylinders by a neural network approach , 1999, IEEE Trans. Geosci. Remote. Sens..

[29]  P. M. Berg,et al.  A contrast source inversion method , 1997 .

[30]  Ce Liu,et al.  Deep Convolutional Neural Network for Image Deconvolution , 2014, NIPS.

[31]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[32]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[33]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[34]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[36]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.