Enhanced Two-Step Deep-Learning Approach for Electromagnetic-Inverse-Scattering Problems: Frequency Extrapolation and Scatterer Reconstruction

Zhang, Huan Huan; Yao, He Ming; Jiang, Li Jun; Ng, Michael K.

doi:10.1109/tap.2022.3225532

Cited by 17 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the second step, the predicted multi-frequency scattered field information was further inputted to a deep convolutional encoder-decoder, which was used to reconstruct the exact dielectric constant distribution. In the numerical results, it was confirmed that this method could accurately reconstruct inhomogeneous and high-contrast scatterers [67].…”

Section: Introductionmentioning

confidence: 58%

Microwave Imaging of Anisotropic Objects by Artificial Intelligence Technology

Liao,

Chiu,

Chen

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper, we present the microwave imaging of anisotropic objects by artificial intelligence technology. Since the biaxial anisotropic scatterers have different dielectric constant components in different transverse directions, the problems faced by transverse electronic (TE) polarization waves are more complex than those of transverse magnetic (TM) polarization waves. In other words, measured scattered field information can scarcely reconstruct microwave images due to the high nonlinearity characteristic of TE polarization. Therefore, we first use the dominant current scheme (DCS) and the back-propagation scheme (BPS) to compute the initial guess image. We then apply a trained convolution neural network (CNN) to regenerate the microwave image. Numerical results show that the CNN possesses a good generalization ability under limited training data, which could be favorable to deploy in image processing. Finally, we compare DCS and BPS reconstruction images for anisotropic objects by the CNN and prove that DCS is better than BPS. In brief, successfully reconstructing biaxial anisotropic objects with a CNN is the contribution of this proposal.

show abstract

Section: Introductionmentioning

confidence: 58%

Microwave Imaging of Anisotropic Objects by Artificial Intelligence Technology

Liao,

Chiu,

Chen

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…While in the artificial intelligence method, it can be used as an approximation method for the initial input image. In the AI mechanism, the data input to the neural network can be categorized as (1) scattered field input [4][5][6] and (2) initial shape (or dielectric) guess input [7][8][9][10][11][12][13][14]. In 2019, Yao introduced a two-stage neural network architecture to deal with the inverse scattering problem.…”

Section: Introductionmentioning

confidence: 99%

“…In 2023, Zhang input a single-frequency scattered field into the deep residual convolutional neural network to expand to multifrequency. This scattered field was next input to a deep convolutional encoder-decoder for electromagnetic imaging [6]. Numerical results showed that the reconstruction was good.…”

Section: Introductionmentioning

confidence: 99%

Application of Self-Attention Generative Adversarial Network for Electromagnetic Imaging in Half-Space

Chiu,

Lee,

Chen

et al. 2024

Sensors

View full text Add to dashboard Cite

In this paper, we introduce a novel artificial intelligence technique with an attention mechanism for half-space electromagnetic imaging. A dielectric object in half-space is illuminated by TM (transverse magnetic) waves. Since measurements can only be made in the upper space, the measurement angle will be limited. As a result, we apply a back-propagation scheme (BPS) to generate an initial guessed image from the measured scattered fields for scatterer buried in the lower half-space. This process can effectively reduce the high nonlinearity of the inverse scattering problem. We further input the guessed images into the generative adversarial network (GAN) and the self-attention generative adversarial network (SAGAN), respectively, to compare the reconstruction performance. Numerical results prove that both SAGAN and GAN can reconstruct dielectric objects and the MNIST dataset under same measurement conditions. Our analysis also reveals that SAGAN is able to reconstruct electromagnetic images more accurately and efficiently than GAN.

show abstract