Deep Learning of Crystalline Defects from TEM images: A Solution for the Problem of “Never Enough Training Data”

This research presents a novel approach to analyzing crystalline defects in metallic devices using deep learning. The authors developed a parametric model for generating synthetic training data to segment dislocations, overcoming the limitations of manual annotation in Transmission Electron Microscopy (TEM). The study also introduces an enhanced deep learning method optimized for segmenting overlapping or intersecting dislocation lines. The results demonstrate the potential of synthetic data in providing more efficient and accurate analysis of dislocation microstructures.

Publication date: July 12, 2023
Project Page: N/A
Paper: https://arxiv.org/pdf/2307.06322.pdf