Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-644758

D-CNN and VQ-VAE Autoencoders for Compression and Denoising of Industrial X-Ray Computed Tomography Images

  • The ever-growing volume of data in imaging sciences stemming from advancements in imaging technologies, necessitates efficient and reliable storage solutions for such large datasets. This study investigates the compression of industrial X-ray computed tomography (XCT) data using deep learning autoencoders and examines how these compression algorithms affect the quality of the recovered data. Two network architectures with different compression rates were used, a deep convolution neural network (D-CNN) and a vector quantized variational autoencoder (VQ-VAE). The XCT data used was from a sandstone sample with a complex internal pore network as a good test case for the importance of feature preservation. The quality of the decoded images obtained from the two different deep learning architectures with different compression rates were quantified and compared to the original input data. In addition, to improve image decoding quality metrics, we introduced a metric sensitive to edgeThe ever-growing volume of data in imaging sciences stemming from advancements in imaging technologies, necessitates efficient and reliable storage solutions for such large datasets. This study investigates the compression of industrial X-ray computed tomography (XCT) data using deep learning autoencoders and examines how these compression algorithms affect the quality of the recovered data. Two network architectures with different compression rates were used, a deep convolution neural network (D-CNN) and a vector quantized variational autoencoder (VQ-VAE). The XCT data used was from a sandstone sample with a complex internal pore network as a good test case for the importance of feature preservation. The quality of the decoded images obtained from the two different deep learning architectures with different compression rates were quantified and compared to the original input data. In addition, to improve image decoding quality metrics, we introduced a metric sensitive to edge preservation, which is crucial for three-dimensional data analysis. We showed that different architectures and compression rates are required depending on the specific characteristics needed to be preserved for later analysis. The findings presented here can aid scientists in determining the requirements and strategies needed for appropriate data storage and analysis.zeige mehrzeige weniger

Volltext Dateien herunterladen

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Bardia HejaziORCiD, Keerthana ChandORCiD, Tobias FritschORCiD, Giovanni BrunoORCiD
Dokumenttyp:Buchkapitel
Veröffentlichungsform:Verlagsliteratur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):Frontiers in Artificial Intelligence and Applications
Jahr der Erstveröffentlichung:2025
Organisationseinheit der BAM:8 Zerstörungsfreie Prüfung
8 Zerstörungsfreie Prüfung / 8.5 Röntgenbildgebung
Veröffentlichende Institution:Bundesanstalt für Materialforschung und -prüfung (BAM)
Verlag:IOS Press
Erste Seite:1
Letzte Seite:8
DDC-Klassifikation:Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten
Freie Schlagwörter:Data Compression; Deep Learning; X-ray Computed Tomography
Themenfelder/Aktivitätsfelder der BAM:Material
Material / Additive Fertigung
Veranstaltung:28th European Conference on Artificial Intelligence – Including 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025)
Veranstaltungsort:Bologna, Italy
Beginndatum der Veranstaltung:25.10.2025
Enddatum der Veranstaltung:30.10.2025
DOI:10.3233/FAIA251480
URN:urn:nbn:de:kobv:b43-644758
URL:https://ebooks.iospress.nl/doi/10.3233/FAIA251480
ISSN:0922-6389
Verfügbarkeit des Dokuments:Datei für die Öffentlichkeit verfügbar ("Open Access")
Lizenz (Deutsch):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
Datum der Freischaltung:27.10.2025
Referierte Publikation:Nein
Schriftenreihen ohne Nummerierung:Wissenschaftliche Artikel 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.