Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor

Muhammad Zaid; Patrick Gaydecki; Sung Quek; Graham Miller; Bosco Fernandes

doi:10.1063/1.1916761

Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor

Muhammad Zaid^*, Patrick Gaydecki, Sung Quek, Graham Miller, Bosco Fernandes

^*Corresponding author for this work

University of Manchester (UOM)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper describes a novel methodology to reduce the scanning time and to extract bar dimensional information from images generated by an inductive sensor. Using a sparsely populated data set obtained from a reduced number of scan lines, faster high resolution images are generated using image interpolation techniques. Having generated these images, image filtering, peak picking and neural networks methods are applied to extract bar dimensional information and accurate 3 D visualization.

Original language	English
Title of host publication	Review of Progress in Quantitative Nondestructive Evaluation Volume 24
Pages	836-843
Number of pages	8
Volume	760
DOIs	https://doi.org/10.1063/1.1916761
Publication status	Published - 9 Apr 2005
Event	Review of Progress in Quantitative Nondestructive Evaluation - Golden, CO, United States Duration: 25 Jul 2004 → 30 Jul 2004

Conference

Conference	Review of Progress in Quantitative Nondestructive Evaluation
Country/Territory	United States
City	Golden, CO
Period	25/07/04 → 30/07/04

Access to Document

10.1063/1.1916761

Cite this

@inproceedings{5e0ce668fb724c4c8dec8e2921e5a850,

title = "Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor",

abstract = "This paper describes a novel methodology to reduce the scanning time and to extract bar dimensional information from images generated by an inductive sensor. Using a sparsely populated data set obtained from a reduced number of scan lines, faster high resolution images are generated using image interpolation techniques. Having generated these images, image filtering, peak picking and neural networks methods are applied to extract bar dimensional information and accurate 3 D visualization.",

author = "Muhammad Zaid and Patrick Gaydecki and Sung Quek and Graham Miller and Bosco Fernandes",

year = "2005",

month = apr,

day = "9",

doi = "10.1063/1.1916761",

language = "English",

isbn = "0735402450",

volume = "760",

pages = "836--843",

booktitle = "Review of Progress in Quantitative Nondestructive Evaluation Volume 24",

note = "Review of Progress in Quantitative Nondestructive Evaluation ; Conference date: 25-07-2004 Through 30-07-2004",

}

Zaid, M, Gaydecki, P, Quek, S, Miller, G & Fernandes, B 2005, Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor. in Review of Progress in Quantitative Nondestructive Evaluation Volume 24. vol. 760, pp. 836-843, Review of Progress in Quantitative Nondestructive Evaluation, Golden, CO, United States, 25/07/04. https://doi.org/10.1063/1.1916761

Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor. / Zaid, Muhammad; Gaydecki, Patrick; Quek, Sung et al.
Review of Progress in Quantitative Nondestructive Evaluation Volume 24. Vol. 760 2005. p. 836-843.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor

AU - Zaid, Muhammad

AU - Gaydecki, Patrick

AU - Quek, Sung

AU - Miller, Graham

AU - Fernandes, Bosco

PY - 2005/4/9

Y1 - 2005/4/9

N2 - This paper describes a novel methodology to reduce the scanning time and to extract bar dimensional information from images generated by an inductive sensor. Using a sparsely populated data set obtained from a reduced number of scan lines, faster high resolution images are generated using image interpolation techniques. Having generated these images, image filtering, peak picking and neural networks methods are applied to extract bar dimensional information and accurate 3 D visualization.

AB - This paper describes a novel methodology to reduce the scanning time and to extract bar dimensional information from images generated by an inductive sensor. Using a sparsely populated data set obtained from a reduced number of scan lines, faster high resolution images are generated using image interpolation techniques. Having generated these images, image filtering, peak picking and neural networks methods are applied to extract bar dimensional information and accurate 3 D visualization.

UR - http://www.scopus.com/inward/record.url?scp=33748552957&partnerID=8YFLogxK

U2 - 10.1063/1.1916761

DO - 10.1063/1.1916761

M3 - Conference contribution

AN - SCOPUS:33748552957

SN - 0735402450

SN - 9780735402454

VL - 760

SP - 836

EP - 843

BT - Review of Progress in Quantitative Nondestructive Evaluation Volume 24

T2 - Review of Progress in Quantitative Nondestructive Evaluation

Y2 - 25 July 2004 through 30 July 2004

ER -

Fourier interpolation and neural network analysis for accurate 3D reconstruction of images produced by an inductive sensor

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this