Model-based methods for textile fault detection

J. G. Campbell, C. Fraley, D. Stanford, F. Murtagh, A. E. Raftery

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Addressing the problem of automatic fault detection in woven and dyed fabric, we discuss a number of new statistical model-based methods and relate them to a first stage of point/local detection and a second stage of extended pattern detection. One model-based method defines a maximum likelihood binarization of the image. In another model-based method, we describe a discrete Fourier transform-based texture analysis technique that is highly effective for woven textiles in discriminating subtle flaw patterns from the pronounced background of repetitive weaving pattern and random clutter. Finally, we describe a model-based clustering method that can be employed to aggregate perceptual groupings of point and local detections.

Original languageEnglish
Pages (from-to)339-346
Number of pages8
JournalInternational Journal of Imaging Systems and Technology
Volume10
Issue number4
DOIs
Publication statusPublished - 2 Jul 1999
Externally publishedYes

Fingerprint

Fault detection
Textiles
Discrete Fourier transforms
Maximum likelihood
Textures
Defects

Cite this

Campbell, J. G. ; Fraley, C. ; Stanford, D. ; Murtagh, F. ; Raftery, A. E. / Model-based methods for textile fault detection. In: International Journal of Imaging Systems and Technology. 1999 ; Vol. 10, No. 4. pp. 339-346.
@article{0155925012a246d4921af00833444792,
title = "Model-based methods for textile fault detection",
abstract = "Addressing the problem of automatic fault detection in woven and dyed fabric, we discuss a number of new statistical model-based methods and relate them to a first stage of point/local detection and a second stage of extended pattern detection. One model-based method defines a maximum likelihood binarization of the image. In another model-based method, we describe a discrete Fourier transform-based texture analysis technique that is highly effective for woven textiles in discriminating subtle flaw patterns from the pronounced background of repetitive weaving pattern and random clutter. Finally, we describe a model-based clustering method that can be employed to aggregate perceptual groupings of point and local detections.",
author = "Campbell, {J. G.} and C. Fraley and D. Stanford and F. Murtagh and Raftery, {A. E.}",
year = "1999",
month = "7",
day = "2",
doi = "10.1002/(SICI)1098-1098(1999)10:4<339::AID-IMA5>3.0.CO;2-3",
language = "English",
volume = "10",
pages = "339--346",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

Model-based methods for textile fault detection. / Campbell, J. G.; Fraley, C.; Stanford, D.; Murtagh, F.; Raftery, A. E.

In: International Journal of Imaging Systems and Technology, Vol. 10, No. 4, 02.07.1999, p. 339-346.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Model-based methods for textile fault detection

AU - Campbell, J. G.

AU - Fraley, C.

AU - Stanford, D.

AU - Murtagh, F.

AU - Raftery, A. E.

PY - 1999/7/2

Y1 - 1999/7/2

N2 - Addressing the problem of automatic fault detection in woven and dyed fabric, we discuss a number of new statistical model-based methods and relate them to a first stage of point/local detection and a second stage of extended pattern detection. One model-based method defines a maximum likelihood binarization of the image. In another model-based method, we describe a discrete Fourier transform-based texture analysis technique that is highly effective for woven textiles in discriminating subtle flaw patterns from the pronounced background of repetitive weaving pattern and random clutter. Finally, we describe a model-based clustering method that can be employed to aggregate perceptual groupings of point and local detections.

AB - Addressing the problem of automatic fault detection in woven and dyed fabric, we discuss a number of new statistical model-based methods and relate them to a first stage of point/local detection and a second stage of extended pattern detection. One model-based method defines a maximum likelihood binarization of the image. In another model-based method, we describe a discrete Fourier transform-based texture analysis technique that is highly effective for woven textiles in discriminating subtle flaw patterns from the pronounced background of repetitive weaving pattern and random clutter. Finally, we describe a model-based clustering method that can be employed to aggregate perceptual groupings of point and local detections.

UR - http://www.scopus.com/inward/record.url?scp=0032630236&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1098-1098(1999)10:4<339::AID-IMA5>3.0.CO;2-3

DO - 10.1002/(SICI)1098-1098(1999)10:4<339::AID-IMA5>3.0.CO;2-3

M3 - Article

VL - 10

SP - 339

EP - 346

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 4

ER -