Unsupervised Learning for the Automatic Counting of Grains in Nanocrystals and Image Segmentation at the Atomic Resolution

Identifying the grain distribution and grain boundaries of nanoparticles is important for predicting their properties. Experimental methods for identifying the crystallographic distribution, such as precession electron diffraction, are limited by their probe size. In this study, we developed an unsu...

Full description

Saved in:
Bibliographic Details
Published in:Nanomaterials (Basel, Switzerland) Switzerland), 2024-10, Vol.14 (20), p.1614
Main Authors: Sohn, Woonbae, Kim, Taekyung, Moon, Cheon Woo, Shin, Dongbin, Park, Yeji, Jin, Haneul, Baik, Hionsuck
Format: Article
Language:English
Subjects:
Accuracy
Atomic properties
automated image segmentation
Automation
Cluster analysis
Clustering
Crystallography
Data analysis
Datasets
Electron diffraction
Electrons
Experimental methods
Fourier transforms
Gabor filter
Gabor filters
Grain boundaries
Image filters
Image processing
Image segmentation
K-means clustering
Machine learning
Methods
Nanoparticles
Polycrystals
Transmission electron microscopy
Unsupervised learning
Vector quantization
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Identifying the grain distribution and grain boundaries of nanoparticles is important for predicting their properties. Experimental methods for identifying the crystallographic distribution, such as precession electron diffraction, are limited by their probe size. In this study, we developed an unsupervised learning method by applying a Gabor filter to HAADF-STEM images at the atomic level for image segmentation and automatic counting of grains in polycrystalline nanoparticles. The methodology comprises a Gabor filter for feature extraction, non-negative matrix factorization for dimension reduction, and K-means clustering. We set the threshold distance and angle between the clusters required for the number of clusters to converge so as to automatically determine the optimal number of grains. This approach can shed new light on the nature of polycrystalline nanoparticles and their structure-property relationships.
ISSN:2079-4991
2079-4991
DOI:10.3390/nano14201614