English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A deep learning-assisted inversion method is proposed to solve theinhomogeneous background imaging problem. Three non-iterative methods, namelythe distorted-Born (DB) major current coefficients method, the DB modified Bornapproximation method, and the DB connection method, are introduced to addressthe inhomogeneous background inverse scattering problem. These methods retainthe multiple scattering information by utilizing the major current obtainedthrough singular value decomposition of the Green's function and the scatteredfield, without resourcing to optimization techniques. As a result, the proposedmethods offer improved reconstruction resolution and accuracy for unknownobjects embedded in inhomogeneous backgrounds, surpassing the backpropagationscheme (BPS) and Born approximation (BA) method that disregard the multiplescattering effect. To further enhance the resolution and accuracy of thereconstruction, a Shifted-Window (Swin) transformer network is employed forcapturing super-resolution information in the images. The attention mechanismincorporated in the shifted window facilitates global interactions betweenobjects, thereby enhancing the performance of the inhomogeneous backgroundimaging algorithm while reducing computational complexity. Moreover, anadaptive training method is proposed to enhance the generalization ability ofthe network. The effectiveness of the proposed methods is demonstrated throughboth synthetic data and experimental data. Notably, super-resolution imaging isachieved with quasi real-time speed, indicating promising application potentialfor the proposed algorithms.

Non-iterative Methods in Inhomogeneous Background Inverse Scattering Imaging Problem Assisted by Swin Transformer Network