{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:00:05Z","timestamp":1785416405726,"version":"3.56.0"},"reference-count":20,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science and Technology Council","award":["114-2221-E-032-018"],"award-info":[{"award-number":["114-2221-E-032-018"]}]},{"award":["114-2221-E-032-018"],"award-info":[{"award-number":["114-2221-E-032-018"]}],"id":[{"id":"https:\/\/ror.org\/02kv4zf79","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Reconstructing high-resolution images of anisotropic targets in microwave imaging remains a challenging problem due to the strong directionality of electromagnetic responses and the inherent nonlinearity of the inverse scattering process. To address these issues, we propose a novel Perceptual Generative Adversarial Network (PGAN) enhanced with a Self-Attention mechanism for anisotropic electromagnetic imaging. The perceptual loss encourages the preservation of high-level structural features, while the Self-Attention module enables the model to capture long-range dependencies and directional correlations that are critical in representing anisotropic material distributions. This joint architecture is trained to refine coarse permittivity estimates obtained from conventional Back-Propagation Schemes (BPSs). Numerical simulations and validation using measured experimental data demonstrate that the proposed method achieves improved reconstruction accuracy and structural similarity compared with the PGAN without SA and U-Net. In particular, PGAN with SA reduces the Root Mean Square Error (RMSE) by 15.1% and improves the Structural Similarity Index Measure (SSIM) by 3.8%, confirming its effectiveness in recovering fine-scale details and enhancing reconstruction quality. These results suggest that the proposed framework offers a promising solution for robust and high-resolution electromagnetic imaging in geophysical and remote sensing applications.<\/jats:p>","DOI":"10.3390\/s26123705","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:59:31Z","timestamp":1781146771000},"page":"3705","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Electromagnetic Imaging of Anisotropic Objects Using a Self-Attention Perceptual Generative Adversarial Network"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1900-5907","authenticated-orcid":false,"given":"Po-Hsiang","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Tamkang University, Tamsui 251301, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4342-6461","authenticated-orcid":false,"given":"Chien-Ching","family":"Chiu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Tamkang University, Tamsui 251301, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang-Han","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Tamkang University, Tamsui 251301, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng Hock","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic, University Tunku Abdul Rahman, Kajang 43200, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Daniels, D.J. (2004). Ground Penetrating Radar, IET. [2nd ed.].","DOI":"10.1049\/PBRA015E"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Pastorino, M. (2010). Microwave Imaging, Wiley.","DOI":"10.1002\/9780470602492"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"074004","DOI":"10.1088\/0266-5611\/26\/7\/074004","article-title":"The inverse electromagnetic scattering problem for anisotropic media","volume":"26","author":"Cakoni","year":"2010","journal-title":"Inverse Probl."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1109\/LSP.2016.2579647","article-title":"A recursive Born approach to nonlinear inverse scattering","volume":"23","author":"Kamilov","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113272","DOI":"10.1016\/j.jcp.2024.113272","article-title":"Electromagnetic inverse wave scattering in anisotropic media via reduced order modeling","volume":"515","author":"Borcea","year":"2024","journal-title":"J. Comput. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/LGRS.2007.900735","article-title":"Through-wall imaging via a linear inverse scattering algorithm","volume":"4","author":"Soldovieri","year":"2007","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/TAP.2009.2035997","article-title":"A sparsity regularization approach to the electromagnetic inverse scattering problem","volume":"58","author":"Winters","year":"2010","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_9","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Guo, L., Song, G., and Wu, H. (2021). Complex-valued Pix2Pix\u2014Deep neural network for nonlinear electromagnetic inverse scattering. Electronics, 10.","DOI":"10.3390\/electronics10060752"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1109\/TAP.2021.3111281","article-title":"Physical model-inspired deep unrolling network for solving nonlinear inverse scattering problems","volume":"70","author":"Liu","year":"2022","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2008414","DOI":"10.1109\/TGRS.2022.3222502","article-title":"Electromagnetic imaging of uniaxial objects by artificial intelligence technology","volume":"60","author":"Chiu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1109\/TAP.2022.3225532","article-title":"Enhanced two-step deep-learning approach for electromagnetic inverse scattering problems: Frequency extrapolation and scatterer reconstruction","volume":"71","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6133","DOI":"10.1109\/TAP.2024.3388205","article-title":"Enhanced deep learning approach based on the conditional generative adversarial network for electromagnetic inverse scattering problems","volume":"72","author":"Yao","year":"2024","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2384","DOI":"10.1109\/TMTT.2022.3228945","article-title":"Learning-assisted inversion for solving nonlinear inverse scattering problem","volume":"71","author":"Xu","year":"2023","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_17","first-page":"2000514","article-title":"A physics-assisted deep-learning scheme based on globally perceptive modules for electromagnetic inverse scattering problems","volume":"63","author":"Du","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1290","DOI":"10.1109\/TMTT.2024.3436023","article-title":"Attention-Unet for electromagnetic inverse scattering problems in microwave imaging","volume":"73","author":"Zakaria","year":"2025","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"S117","DOI":"10.1088\/0266-5611\/21\/6\/S09","article-title":"Free space experimental scattering database continuation: Experimental set-up and measurement precision","volume":"21","author":"Geffrin","year":"2005","journal-title":"Inverse Probl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1109\/TCI.2021.3093793","article-title":"Electromagnetic Inverse Scattering with Perceptual Generative Adversarial Networks","volume":"7","author":"Song","year":"2021","journal-title":"IEEE Trans. Comput. Imaging"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3705\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:14:11Z","timestamp":1781842451000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":20,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123705"],"URL":"https:\/\/doi.org\/10.3390\/s26123705","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]}}}