Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-654043

Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks

  • Terahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images. Conventional image processing techniques cannot simultaneously address both issues, and manual intervention is often required due to the unknown boundary between denoising and deblurring. To tackle this challenge, we propose a principal component analysis (PCA)-based THz self-supervised denoising and deblurring network (THz-SSDD). The network employs a Recorrupted-to-Recorrupted self-supervised learning strategy to capture the intrinsic features of noise by exploiting invariance under repeated corruption. PCA decomposition and reconstruction are then applied to restore images across both low and high frequencies. The performance of the THz-SSDD network was evaluated on four types of samples. Training requires only a small set of unlabeled noisy images, and testing across samples with different material properties andTerahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images. Conventional image processing techniques cannot simultaneously address both issues, and manual intervention is often required due to the unknown boundary between denoising and deblurring. To tackle this challenge, we propose a principal component analysis (PCA)-based THz self-supervised denoising and deblurring network (THz-SSDD). The network employs a Recorrupted-to-Recorrupted self-supervised learning strategy to capture the intrinsic features of noise by exploiting invariance under repeated corruption. PCA decomposition and reconstruction are then applied to restore images across both low and high frequencies. The performance of the THz-SSDD network was evaluated on four types of samples. Training requires only a small set of unlabeled noisy images, and testing across samples with different material properties and measurement modes demonstrates effective denoising and deblurring. Quantitative analysis further validates the network’s feasibility, showing improvements in image quality while preserving the physical characteristics of the original signals.zeige mehrzeige weniger

Volltext Dateien herunterladen

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Pengfei ZhuORCiD, Xavier Maldague
Dokumenttyp:Preprint
Veröffentlichungsform:Graue Literatur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):arXiv.org
Jahr der Erstveröffentlichung:2026
Organisationseinheit der BAM:8 Zerstörungsfreie Prüfung
8 Zerstörungsfreie Prüfung / 8.3 Thermografische Verfahren
Veröffentlichende Institution:Bundesanstalt für Materialforschung und -prüfung (BAM)
Verlag:Cornell University
Verlagsort:Ithaca, NY
Aufsatznummer:arXiv:2601.12149
Erste Seite:1
Letzte Seite:9
DDC-Klassifikation:Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurbau
Freie Schlagwörter:Deblurring; Denoising; Non-destructive testing (NDT); Self-supervised learning; Terahertz
Themenfelder/Aktivitätsfelder der BAM:Infrastruktur
Infrastruktur / Leichtbau
DOI:10.48550/arXiv.2601.12149
URN:urn:nbn:de:kobv:b43-654043
ISSN:2331-8422
Verfügbarkeit des Dokuments:Datei für die Öffentlichkeit verfügbar ("Open Access")
Lizenz (Deutsch):License LogoAllgemeines Deutsches Urheberrecht
Datum der Freischaltung:26.01.2026
Referierte Publikation:Nein
Schriftenreihen ohne Nummerierung:Preprints der BAM
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.