TY - CONF A1 - Hejazi, Bardia T1 - X-ray Computed Tomography Image Compression and Denoising with AI N2 - The ever-growing volume of data in imaging sciences stemming from advancements in imaging technology, necessitates efficient and reliable storage solutions for such large datasets. In this study, we investigated the compression of industrial X-ray computed tomography (XCT) data using deep learning and examined how these compression algorithms affect the quality of the recovered data. To determine best strategies, we investigated two different network architectures with different compression rates. The XCT data used was from a sandstone sample with a complex internal pore network. The quality of the recovered images obtained from the two different deep learning architectures with different compression rates were quantified and compared to the original input data. We showed that the most suitable architecture and compression rate can change, depending on what specific characteristics we would need to preserve for later analysis. The findings presented here can aid scientists in determining the best approaches and strategies for their data storage and analysis requirements. T2 - BAM AI & ML Symposium CY - Berlin, Germany DA - 06.11.2025 KW - X-ray computed tomography KW - Compression KW - Deep Learning PY - 2025 AN - OPUS4-65610 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Léonard, Fabien T1 - On nominal-actual comparisons for additive manufacturing applications N2 - Nominal-actual comparisons are routinely performed to compare a manufactured specimen to a reference specimen. X-ray Computed Tomography (CT) has brought a profound change in the way that tolerance verifications are performed in industry, by allowing the inner and outer geometries of an object to be measured, without the need for external access or destructive testing. As a results, CT is increasingly used in additive manufacturing applications, where a nominal-actual comparison performed between the digital model (CAD file), used as an input for the 3D printer, and the CT volume from the printed part, can provide invaluable information as to the accuracy of the printing process. However, the nominal-actual comparison process is somewhat different when applied to additively manufactured specimens by comparison to conventionally manufactured specimens. T2 - 9th Conference on Industrial Computed Tomography CY - Padova, Italy DA - 14.02.2019 KW - Computed tomography KW - X-ray computed tomography PY - 2019 AN - OPUS4-47833 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Léonard, Fabien T1 - Metrology for Additively Manufactured Medical Implants: The MetAMMI project N2 - Additive manufacturing (AM) offers an effective solution to the medical sector. It enables the production, on demand, of customised implants which match the patient’s anatomy, with grafts that promote bone growth, as well as surgical guides that help the surgeons. The objective of this project is to provide a comprehensive basis to enable the safe use of medical AM products with traceable and reliable dimensionalmeasurements. This will guarantee the reliability of medical AM products to notified bodies and facilitate acceptance of AM in the medical sector for a better quality of life. T2 - BPWT/BAM Workshop " Innovative Materialien und Qualitätskontrolle für additive Fertigung" CY - Berlin, Germany DA - 12.09.2018 KW - Additive manufacturing KW - X-ray computed tomography PY - 2018 AN - OPUS4-45926 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -