Machine learning-based multidomain processing for texture-based image segmentation and analysis

Atomic and molecular resolved atomic force microscopy (AFM) images offer unique insights into materials' properties such as local ordering, molecular orientation, and topological defects, which can be used to pinpoint physical and chemical interactions occurring at the surface. Utilizing machin...

Full description

Saved in:
Bibliographic Details
Published in:Applied physics letters 2020-01, Vol.116 (4)
Main Authors: Borodinov, Nikolay, Tsai, Wan-Yu, Korolkov, Vladimir V., Balke, Nina, Kalinin, Sergei V., Ovchinnikova, Olga S.
Format: Article
Language:English
Subjects:
Applied physics
Atomic force microscopy
Crystal defects
Crystal structure
Data processing
Feature extraction
Image analysis
Image classification
Image segmentation
Machine learning
Microscopes
Organic chemistry
Orientation
Parameters
Physical properties
Qualitative analysis
Robustness (mathematics)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Atomic and molecular resolved atomic force microscopy (AFM) images offer unique insights into materials' properties such as local ordering, molecular orientation, and topological defects, which can be used to pinpoint physical and chemical interactions occurring at the surface. Utilizing machine learning for extracting underlying physical parameters increases the throughput of AFM data processing and eliminates inconsistencies intrinsic to manual image analysis, thus enabling the creation of reliable frameworks for qualitative and quantitative evaluation of experimental data. Here, we present a robust and scalable approach to the segmentation of AFM images based on flexible pre-selected classification criteria. The usage of supervised learning and feature extraction allows us to retain the consideration of specific problem-dependent features (such as types of periodical structures observed in the images and the associated numerical parameters: spacing, orientation, etc.). We highlight the applicability of this approach for the segmentation of molecular resolved AFM images based on the crystal orientation of the observed domains, automated selection of boundaries, and collection of relevant statistics. Overall, we outline a general strategy for machine learning-enabled analysis of nanoscale systems exhibiting periodic order that could be applied to any analytical imaging technique.
ISSN:0003-6951
1077-3118
DOI:10.1063/1.5135328