Machine Learning Pipeline for Segmentation and Defect Identification from High-Resolution Transmission Electron Microscopy Data

• Published in: Microscopy and microanalysis Vol. 27; no. 3; pp. 549 - 556
• Main Authors: Groschner, Catherine K., Choi, Christina, Scott, Mary C.
• Format: Journal Article
• Language: English
• Published: New York, USA Cambridge University Press 01.06.2021; Oxford University Press
• Subjects: Automation; Cadmium selenide; Data interpretation; Datasets; Deep learning; Fault detection; High resolution; High resolution electron microscopy; Image acquisition; Image processing; Image segmentation; Image transmission; Learning algorithms; Machine learning; Morphology; Nanomaterials; Nanoparticles; Neural networks; Pipelines; Software and Instrumentation; Source code; Stacking faults; Statistical distributions; Transmission electron microscopy; deep learning; segmentation; structure classification; automated analysis; HRTEM

In the field of transmission electron microscopy, data interpretation often lags behind acquisition methods, as image processing methods often have to be manually tailored to individual datasets. Machine learning offers a promising approach for fast, accurate analysis of electron microscopy data. He...