Fast subpixel digital image correlation using artificial neural networks

M. C. Pitter; C. W. See; Michael Geoffrey Somekh

Fast subpixel digital image correlation using artificial neural networks

M. C. Pitter, C. W. See, Michael Geoffrey Somekh

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

11 Citations (Scopus)

Abstract

Digital image correlation has been used to measure microscopic deformation in thermally stressed microelectronics devices. Displacement precisions of better than 0.03 pixels have been achieved by combining nonintegral pixel shifting of subimages and artificial neural networks (ANNs). The ANNs are trained to estimate the subpixel element of the object displacement from the digital correlation. Although similar accuracies can be obtained by curve-fitting to the correlation peaks and differentiating, the neural approach has the advantage that it allows fast subpixel displacement analysis over a range of object textures without knowledge of the analytical form of the correlation peaks.

Original language	English
Title of host publication	IEEE International Conference on Image Processing
Pages	901-904
Number of pages	4
Publication status	Published - 1 Jan 2001
Externally published	Yes
Event	IEEE International Conference on Image Processing (ICIP) - Thessaloniki, Greece Duration: 7 Oct 2001 → 10 Oct 2001

Conference

Conference	IEEE International Conference on Image Processing (ICIP)
Country/Territory	Greece
City	Thessaloniki
Period	7/10/01 → 10/10/01

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Hardware and Architecture
Electrical and Electronic Engineering

Cite this

@inproceedings{e7182486914c4269be1d7fa49e48b23c,

title = "Fast subpixel digital image correlation using artificial neural networks",

abstract = "Digital image correlation has been used to measure microscopic deformation in thermally stressed microelectronics devices. Displacement precisions of better than 0.03 pixels have been achieved by combining nonintegral pixel shifting of subimages and artificial neural networks (ANNs). The ANNs are trained to estimate the subpixel element of the object displacement from the digital correlation. Although similar accuracies can be obtained by curve-fitting to the correlation peaks and differentiating, the neural approach has the advantage that it allows fast subpixel displacement analysis over a range of object textures without knowledge of the analytical form of the correlation peaks.",

author = "Pitter, {M. C.} and See, {C. W.} and Somekh, {Michael Geoffrey}",

year = "2001",

month = jan,

day = "1",

language = "English",

pages = "901--904",

booktitle = "IEEE International Conference on Image Processing",

note = "IEEE International Conference on Image Processing (ICIP) ; Conference date: 07-10-2001 Through 10-10-2001",

}

TY - GEN

T1 - Fast subpixel digital image correlation using artificial neural networks

AU - Pitter, M. C.

AU - See, C. W.

AU - Somekh, Michael Geoffrey

PY - 2001/1/1

Y1 - 2001/1/1

N2 - Digital image correlation has been used to measure microscopic deformation in thermally stressed microelectronics devices. Displacement precisions of better than 0.03 pixels have been achieved by combining nonintegral pixel shifting of subimages and artificial neural networks (ANNs). The ANNs are trained to estimate the subpixel element of the object displacement from the digital correlation. Although similar accuracies can be obtained by curve-fitting to the correlation peaks and differentiating, the neural approach has the advantage that it allows fast subpixel displacement analysis over a range of object textures without knowledge of the analytical form of the correlation peaks.

AB - Digital image correlation has been used to measure microscopic deformation in thermally stressed microelectronics devices. Displacement precisions of better than 0.03 pixels have been achieved by combining nonintegral pixel shifting of subimages and artificial neural networks (ANNs). The ANNs are trained to estimate the subpixel element of the object displacement from the digital correlation. Although similar accuracies can be obtained by curve-fitting to the correlation peaks and differentiating, the neural approach has the advantage that it allows fast subpixel displacement analysis over a range of object textures without knowledge of the analytical form of the correlation peaks.

UR - http://www.scopus.com/inward/record.url?scp=0035173276&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 901

EP - 904

BT - IEEE International Conference on Image Processing

T2 - IEEE International Conference on Image Processing (ICIP)

Y2 - 7 October 2001 through 10 October 2001

ER -

Fast subpixel digital image correlation using artificial neural networks

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this