Deep Learning-Enhanced Qualitative Microwave Imaging: Rationale and Initial Assessment

Yago, Alvaro; Cavagnaro, Marta; Crocco, Lorenzo

doi:10.23919/eucap51087.2021.9411361

Cited by 12 publications

(9 citation statements)

References 19 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To assess the quality of the approximation, we considered different quality measures such as the accuracy parameter (ACC), the Dice similarity coefficient (DSC), and Matthews correlation coefficient (MC), all described in [36], [37]. Those metrics are defined for binarized images, which are obtained by setting the pixels whose value is above the adopted threshold to one, and setting to zero remaining pixels.…”

Section:    Smentioning

confidence: 99%

“…The algorithm was defined for the two-dimensional (2D) geometry, but the extension to the three-dimensional (3D) geometry would be straightforward. To study the effect of the polynomial order and number of domains on the image reconstruction, we considered several figures of merit, such as the Dice similarity coefficient (DSC) and Matthews correlation coefficient (MC) [36], [37].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Smooth Polynomial Approach for Microwave Imaging in Sparse Processing Framework

2022

View full text Add to dashboard Cite

We developed a novel qualitative imaging algorithm based on a polynomial approximation of the unknown contrast and sparse (l 1 ) regularization. Contrary to previously published results, we defined polynomial basis functions on subdomains that divide the investigation domain. Moreover, we formulated constraints that ensure the continuity of the contrast on subdomain borders. We showed that the proposed algorithm improved imaging resolution, particularly in multiple target scenarios. We demonstrated that partitioning the investigation domain together with contrast continuity formulation enhanced the numerical stability and reduced the computation time. The obtained results were significantly less sensitive to the regularization parameter values than those obtained using the standard polynomial approximation. Namely, smaller domains allow lower polynomial orders, which are numerically more favorable. Continuity constraints reduce the search space and mitigate the occurrence of false solutions. Another contribution of this study is a novel strategy for regularization parameter selection. We considered different figures of merit and numerical scenarios to study the influence of various parameters involved in the imaging process, such as the polynomial order and number of subdomains. An extensive analysis proved the robustness of the approach against noise. The proposed algorithm was designed for two-dimensional geometry. However, generalization to three-dimensional space is straightforward. The algorithm can also be used with other types of regularization such as the l 2 regularization. Potential applications include medical microwave imaging, in which high resolution and noise immunity are vital features.INDEX TERMS Inverse scattering, microwave imaging, polynomial approximation, and sparse processing.

show abstract

Section:    Smentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Smooth Polynomial Approach for Microwave Imaging in Sparse Processing Framework

2022

View full text Add to dashboard Cite

show abstract

“…Preliminary results related to this paper have been presented in [24], where qualitative microwave imaging was combined with the deep learning approach and imaging results were given for a limited number of numerically simulated geometries.…”

Section: Introductionmentioning

confidence: 99%

A Physics-Assisted Deep Learning Microwave Imaging Framework for Real-Time Shape Reconstruction of Unknown Targets

Ruiz

Cavagnaro

Crocco

2022

IEEE Trans. Antennas Propagat.

Self Cite

View full text Add to dashboard Cite

In this paper an innovative approach to microwave imaging, which combines a qualitative imaging technique and deep learning, is presented. The goal is to develop a tool for reliable and user-independent retrieval of the shape of unknown targets from the knowledge of the scattered fields. Qualitative imaging methods are powerful inverse scattering tools, as they provide morphological information in real-time. However, their outcome is a continuous map which has to be hard-thresholded to clearly identify the targets. This thresholding unavoidably results in case-dependent, often user-biased, results. To deal with this issue, a deep learning approach, based on a physics-assisted deep neural network is proposed to automatically classify image pixels, i.e., to generate binary masks, separating the targets (foreground) from the background. In particular, the proposed network binarizes the output of a qualitative imaging inversion technique known as orthogonality sampling method. For the sake of comparison, a deep learning method is also exploited, which generates the binary masks directly from the scattered fields without any qualitative imaging aid. A quantitative assessment of the performances of both methods as well as a test on experimental data are provided.

show abstract

“…In [17], a convolutional neural network (CNN) was combined with an iterative method to retrieve parameters of high-contrast or complicated objects. In [18], a U-Net was trained on regular images, with OSM indicators in the RGB channels as input. No threshold was needed as in conventional OSM, and two adjacent cylinders could be well distinguished with U-Net.…”

Section: Introductionmentioning

confidence: 99%