Unsupervised CNN-based DIC method for 2D displacement measurement

•The paper proposes an unsupervised convolutional neural network (CNN) based DIC method for 2D displacement measurement,which eliminates the need for extensive training data annotation.•A compound loss function that combines the Mean Squared Error (MSE) and Pearson correlation coefficient is designe...

Full description

Bibliographic Details

Published in:	Optics and lasers in engineering Vol. 174; p. 107981
Main Authors:	Wang, Yixiao, Zhou, Canlin
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.03.2024
Subjects:	Convolutional neural network Digital image-correlation Loss function Mean Absolute Error Pearson correlation coefficient Two-dimensional displacement measurement Unsupervised learning Loss function Digital image-correlation Convolutional neural network Mean Absolute Error Two-dimensional displacement measurement Unsupervised learning Pearson correlation coefficient
ISSN:	0143-8166, 1873-0302
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!