Open AccessSubpixel microscopic deformation analysis using correlation and artificial neural networks
Author(s) -
Mark C. Pitter,
C. W. See,
Michael Geoffrey Somekh
Publication year - 2001
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.8.000322
Subject(s) - subpixel rendering , digital image correlation , pixel , displacement (psychology) , deformation (meteorology) , optics , artificial neural network , image processing , artificial intelligence , image resolution , computer science , correlation coefficient , position (finance) , digital image processing , computer vision , materials science , image (mathematics) , physics , psychology , finance , machine learning , economics , composite material , psychotherapist
Microscopic deformation analysis has been performed using digital image correlation and artificial neural networks (ANNs). Cross-correlations of small image regions before and after deformation contain a peak, the position of which indicates the displacement to pixel accuracy. Subpixel resolution has been achieved here by nonintegral pixel shifting and by training ANNs to estimate the fractional part of the displacement. Results from displaced and thermally stressed microelectronic devices indicate these techniques can achieve comparable accuracies to other subpixel techniques and that the use of ANNs can facilitate very fast analysis without knowledge of the analytical form of the image correlation function.