Search NASASearch

DOE OSTI · code-147247

pnnl/defect_detection

Abstract

The code takes expert-labeled segmented images of irradiated and unirradiated pellets and trains DeepConvolutional Neural Networks to segment these images into defects, backgrounds, and boundaries. The code calculated qualitative microstructural information from these segmented images to facilitate the comparison of unirradiated and irradiated pellets

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Oostrom, Marjolein, Pazdernik, Karl, Hagen, Alex. 2024-11-08. pnnl/defect_detection. https://doi.org/10.11578/dc.20241108.1

Cite the original work for its findings. Save a collection to share your selection of sources.