Detection of Microdefects in Fabric with Multifarious Patterns and Colors Using Deep Convolutional Neural Network

Automatic detection of fabric defects is important in textile quality control, particularly in detecting fabrics with multifarious patterns and colors. This study proposes a fabric defect detection system for fabrics with complex patterns and colors. The proposed system comprises five convolutional...

Full description

Saved in:
Bibliographic Details
Published inAdvances in polymer technology Vol. 2024; pp. 1 - 10
Main Authors Xia, Rongfei, Chen, Yifei, Ji, Yangfeng
Format Journal Article
LanguageEnglish
Published Hindawi 12.02.2024
John Wiley & Sons, Inc
Wiley
Subjects
Analysis
Detectors
Neural networks
Quality control
Online AccessGet full text

Cover

Abstract Automatic detection of fabric defects is important in textile quality control, particularly in detecting fabrics with multifarious patterns and colors. This study proposes a fabric defect detection system for fabrics with complex patterns and colors. The proposed system comprises five convolutional layers designed to extract features from the original images effectively. In addition, three fully connected layers are designed to classify the fabric defects into four categories. Using this system, the detection accuracy is improved, and the depth of the model is shortened simultaneously. Optimal detection rates for testing dirty marks, clip marks, broken yams, and defect-free were 88.01%, 90.15%, 98.01%, and 97.73%, respectively. The experimental results show that the proposed method is effective, feasible, and has significant potential for fabric defect detection.
AbstractList Automatic detection of fabric defects is important in textile quality control, particularly in detecting fabrics with multifarious patterns and colors. This study proposes a fabric defect detection system for fabrics with complex patterns and colors. The proposed system comprises five convolutional layers designed to extract features from the original images effectively. In addition, three fully connected layers are designed to classify the fabric defects into four categories. Using this system, the detection accuracy is improved, and the depth of the model is shortened simultaneously. Optimal detection rates for testing dirty marks, clip marks, broken yams, and defect-free were 88.01%, 90.15%, 98.01%, and 97.73%, respectively. The experimental results show that the proposed method is effective, feasible, and has significant potential for fabric defect detection.
Audience Academic
Author Ji, Yangfeng
Xia, Rongfei
Chen, Yifei
Author_xml – sequence: 1
  givenname: Rongfei
  orcidid: 0000-0002-2046-1811
  surname: Xia
  fullname: Xia, Rongfei
  organization: Chengyi CollegeJimei University199 Jimei AvenueXiamen 361021Chinajmu.edu.cn
– sequence: 2
  givenname: Yifei
  surname: Chen
  fullname: Chen, Yifei
  organization: School of Marine EngineeringJimei University176 Shigu RoadXiamen 361021Chinajmu.edu.cn
– sequence: 3
  givenname: Yangfeng
  surname: Ji
  fullname: Ji, Yangfeng
  organization: Chengyi CollegeJimei University199 Jimei AvenueXiamen 361021Chinajmu.edu.cn
BookMark eNp9UctOHDEQtCIiZSG55QN8h2H9GD_miJYQkJYkh3Ae9fixmAw2sb2s-Pt4WcQx6kNJparqVtcxOoopOoS-UnJOqRBLRli_FAOTUugPaEHJoDvG2XCEFkRx0kmphk_ouJQHQijtJV-gv5euOlNDijh5fBtMTtb5xhQcIr6CKQeDd6He49vtXIOHHNK24F9Qq8uxYIgWr9KccsF3JcQNvnTuqTHxOc3bfSzM-Ifb5leou5T_fEYfPczFfXnDE3R39e336rpb__x-s7pYd4YrWjuujODeKduDsXSwfAIlmKKGWaIHa5kG6WgvNDFyGrTjoAjlg7cwMScI8BN0c8i1CR7GpxweIb-MCcL4SqS8GSHXYGY3Sm0EtRaol6RX1E9KU91r4llbR5xsWeeHrA00eYg-1QymjXWPwbQSfGj8hdI9Eb0QohnODob2z1Ky8-8HUDLuuxr3XY1vXTX56UF-H6KFXfi_-h8EHpYC
Cites_doi 10.1186/s40064-016-2452-6
10.1016/j.ins.2018.01.051
10.1117/1.OE.56.9.093104
10.1155/2015/258619
10.1016/j.neucom.2017.06.023
10.1016/j.neuroimage.2017.07.018
10.1016/j.measurement.2022.111665
10.1111/cote.12394
10.1109/WACV.2016.7477593
10.1109/CVPR.2015.7298594
10.1016/j.eswa.2022.116827
10.1155/2021/5592614
10.1016/j.compeleceng.2023.108706
10.1007/978-3-7908-2604-3_16
10.1177/00405175211060081
10.1038/nature14539
10.1162/neco_a_00990
10.5958/1945-919X.2018.00018.X
10.1177/1558925020903026
10.1109/TITS.2017.2732029
10.5604/12303666.1152514
10.1145/3065386
10.1016/S0031-3203(03)00005-0
10.1016/j.eswa.2021.114838
10.17485/ijst/2012/v5i8.12
10.1016/j.aej.2021.08.017
ContentType Journal Article
Copyright Copyright © 2024 Rongfei Xia et al.
COPYRIGHT 2024 John Wiley & Sons, Inc.
Copyright_xml – notice: Copyright © 2024 Rongfei Xia et al.
– notice: COPYRIGHT 2024 John Wiley & Sons, Inc.
DBID RHU
RHW
RHX
AAYXX
CITATION
DOA
DOI 10.1155/2024/5926658
DatabaseName Hindawi Publishing Complete
Hindawi Publishing Subscription Journals
Hindawi Publishing Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

CrossRef
Database_xml – sequence: 1
  dbid: RHX
  name: Hindawi Publishing Open Access
  url: http://www.hindawi.com/journals/
  sourceTypes: Publisher
– sequence: 2
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1098-2329
Editor Ahmad, Nasir M.
Editor_xml – sequence: 1
  givenname: Nasir M.
  surname: Ahmad
  fullname: Ahmad, Nasir M.
EndPage 10
ExternalDocumentID oai_doaj_org_article_68c51dda1f60471fb7818480f21c20e6
A784054555
10_1155_2024_5926658
GrantInformation_xml – fundername: Jimei University
  grantid: CK21018
– fundername: Young and Middle-Aged Teacher Education Research Program of Fujian Province
  grantid: JAT201037
GroupedDBID -~X
.3N
.GA
05W
0R~
10A
1L6
1OB
1OC
1ZS
23M
33P
3SF
3WU
4.4
4ZD
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8FE
8FG
8UM
930
A03
AAESR
AAEVG
AAJEY
AAONW
AAZKR
ABCQN
ABIJN
ABJCF
ABPVW
ACGFO
ACGFS
ACIWK
ACXME
ADBBV
ADEOM
ADIZJ
AEGXH
AEIMD
AENEX
AEUQT
AFBPY
AFKRA
AFZJQ
AIAGR
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
AMBMR
ATUGU
AUFTA
AZBYB
AZVAB
BAFTC
BCNDV
BENPR
BGLVJ
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CS3
D-E
D-F
D1I
DCZOG
DPXWK
DR1
DR2
EBS
F00
F01
F04
G-S
G.N
GNP
GODZA
GROUPED_DOAJ
H.T
H.X
HBH
HCIFZ
HZ~
IAO
IX1
J0M
JPC
KB.
KQQ
LAW
LC2
LC3
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
MK4
MRFUL
MRSTM
MSFUL
MSSTM
N04
N05
N9A
NF~
NNB
O66
O9-
OIG
OK1
P2P
P2W
P2X
P4D
PDBOC
PIMPY
Q.N
Q11
QB0
QRW
R.K
RHU
RHW
RHX
RWB
RWI
RX1
SUPJJ
TUS
UB1
V8K
W8V
W99
WBFHL
WBKPD
WH7
WIB
WIH
WIK
WOHZO
WQJ
WRC
WYISQ
XG1
XV2
~IA
~WT
24P
AAYXX
ACCMX
ADMLS
CITATION
ITC
AAMMB
AEFGJ
AGXDD
AIDQK
AIDYY
ID FETCH-LOGICAL-c371t-37c53fe7d4acd19d3ba75271c2d089dd28a6e14580c6b98e3a70139fdab2e50a3
IEDL.DBID DOA
ISSN 0730-6679
IngestDate Wed Aug 27 01:31:58 EDT 2025
Tue Jun 10 21:05:08 EDT 2025
Tue Jul 01 04:01:40 EDT 2025
Sun Jun 02 18:52:09 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
https://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c371t-37c53fe7d4acd19d3ba75271c2d089dd28a6e14580c6b98e3a70139fdab2e50a3
ORCID 0000-0002-2046-1811
OpenAccessLink https://doaj.org/article/68c51dda1f60471fb7818480f21c20e6
PageCount 10
ParticipantIDs doaj_primary_oai_doaj_org_article_68c51dda1f60471fb7818480f21c20e6
gale_infotracacademiconefile_A784054555
crossref_primary_10_1155_2024_5926658
hindawi_primary_10_1155_2024_5926658
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2024-02-12
PublicationDateYYYYMMDD 2024-02-12
PublicationDate_xml – month: 02
  year: 2024
  text: 2024-02-12
  day: 12
PublicationDecade 2020
PublicationTitle Advances in polymer technology
PublicationYear 2024
Publisher Hindawi
John Wiley & Sons, Inc
Wiley
Publisher_xml – name: Hindawi
– name: John Wiley & Sons, Inc
– name: Wiley
References 22
23
24
26
28
M. D. Zeiler (31) 2012
D. Kingma (33) 2014
J. Duchi (30) 2011; 12
10
11
12
13
14
15
16
17
18
19
L. Bottou (27) 1998
T. Tieleman (32) 2012
1
I. Sutskever (29) 2013; 28
2
3
4
5
6
7
8
9
S. Ioffe (25)
20
21
References_xml – ident: 8
  doi: 10.1186/s40064-016-2452-6
– ident: 14
  doi: 10.1016/j.ins.2018.01.051
– ident: 18
  doi: 10.1117/1.OE.56.9.093104
– ident: 23
  doi: 10.1155/2015/258619
– ident: 24
  doi: 10.1016/j.neucom.2017.06.023
– ident: 15
  doi: 10.1016/j.neuroimage.2017.07.018
– ident: 20
  doi: 10.1016/j.measurement.2022.111665
– ident: 3
  doi: 10.1111/cote.12394
– ident: 17
  doi: 10.1109/WACV.2016.7477593
– ident: 26
  doi: 10.1109/CVPR.2015.7298594
– ident: 6
  doi: 10.1016/j.eswa.2022.116827
– ident: 11
  doi: 10.1155/2021/5592614
– year: 2014
  ident: 33
  article-title: Adam: a method for stochastic optimization
– ident: 21
  doi: 10.1016/j.compeleceng.2023.108706
– volume: 12
  start-page: 2121
  year: 2011
  ident: 30
  article-title: Adaptive subgradient methods for online learning and stochastic optimization
  publication-title: Journal of Machine Learning Research
– ident: 28
  doi: 10.1007/978-3-7908-2604-3_16
– ident: 19
  doi: 10.1177/00405175211060081
– year: 2012
  ident: 32
  article-title: Lecture 6.5—RMSProp, COURSERA: neural networks for machine learning
– ident: 10
  doi: 10.1038/nature14539
– start-page: 9
  volume-title: On-Line Learning in Neural Networks
  year: 1998
  ident: 27
  article-title: Online learning and stochastic approximations
– start-page: 448
  ident: 25
  article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift
– ident: 12
  doi: 10.1162/neco_a_00990
– ident: 16
  doi: 10.5958/1945-919X.2018.00018.X
– ident: 1
  doi: 10.1177/1558925020903026
– ident: 13
  doi: 10.1109/TITS.2017.2732029
– ident: 9
  doi: 10.5604/12303666.1152514
– ident: 22
  doi: 10.1145/3065386
– year: 2012
  ident: 31
  article-title: ADADELTA: an adaptive learning rate method
– ident: 5
  doi: 10.1016/S0031-3203(03)00005-0
– volume: 28
  start-page: 1139
  issue: 3
  year: 2013
  ident: 29
  article-title: On the importance of initialization and momentum in deep learning
  publication-title: Proceedings of Machine Learning Research
– ident: 2
  doi: 10.1016/j.eswa.2021.114838
– ident: 4
  doi: 10.17485/ijst/2012/v5i8.12
– ident: 7
  doi: 10.1016/j.aej.2021.08.017
SSID ssj0011463
Score 2.3219633
Snippet Automatic detection of fabric defects is important in textile quality control, particularly in detecting fabrics with multifarious patterns and colors. This...
SourceID doaj
gale
crossref
hindawi
SourceType Open Website
Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Analysis
Detectors
Neural networks
Quality control
SummonAdditionalLinks – databaseName: Hindawi Publishing Open Access
  dbid: RHX
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8QwEA4qCHoQn7i-yGHFU7Fp8-rR17IIKx4U9lbSZIJ76epu1b_vJNtdVgXxVFpSGmaS-eZrJl8I6YI2iJqSJ9YrmXDNWaIZqMRKBPe8Asji6Q2DB9l_5vdDMWxFkqa_l_AR7QI955eiQCQRepWs4gALpLw_XCwW4GSfqW3myISkKub17T_e_YY8UaB_EYbXXwIB_hwtQUtvm2y1OSG9mjlxh6xAvUs2l5QC98jbLTSxaKqmY08HoYrOQazEoKOa9kyF4YyGf6o07qj1yICR0tPHqJ5ZT6mpHb3BODeZ0lgkQG8BXvFJ_dEOPfx-0OmIl1gYvk-ee3dPN_2kPS0hsbliDUYKK3IPynFjHStcXhklMsVs5lJdOJdpI4FxoVMrq0JDblRI_7wzVQYiNfkBWavHNRwSynzBuSt8kZqwFTXDLMzbXEhdaZeBdR1yPrdk-ToTxSgjmRCiDBYvW4t3yHUw86JNkLKOD9C9ZTszSqmtYM4Z5mWKSOkrhTkE16nPsOspyA65CE4qw4RrJsaadt8AdjVIV5VXCjkq5oFCdEi39eOfvTr6X7NjshFuk3j4ywlZaybvcIoJSFOdxeH3Bceh0gc
  priority: 102
  providerName: Hindawi Publishing
Title Detection of Microdefects in Fabric with Multifarious Patterns and Colors Using Deep Convolutional Neural Network
URI https://dx.doi.org/10.1155/2024/5926658
https://doaj.org/article/68c51dda1f60471fb7818480f21c20e6
Volume 2024
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA6iCHoQn7i-yGHFU7Fp8-pxdV0WcUV8wN5KmkzQS9W16t93ku0ue9KLlxZCaYeZZL6ZdPINIV3QBlFT8sR6JROuOUs0A5VYieCeVwBZ7N4wupXDJ349FuOFVl-hJmxKDzxV3LnUVjDnDPMyRUfqK4UQw3XqM2azFCLZNmLeLJlq_x_g-s9nZe5ChAyfn4sCwSi0dl8AoMjTP_fGq88hD_5-WUCYwSbZaEND2puKtEWWoN4m6wuEgTvkvQ9NrJ2q6auno1BM5yAWZNCXmg5MhV6Nhq1VGg_WekyEMbOnd5FEs_6gpnb0Et3d5IPGWgHaB3jDkfqrnYH4_UDXEW-xPnyXPA2uHi-HSds0IbG5Yg06DCtyD8pxYx0rXF4ZJTKFynKpLpzLtJHAuNCplVWhITcqRIHemSoDkZp8jyzXrzXsE8p8wbkrfJGacCI1w2DM21xIXWmXgXUdcjrTZPk25cYoY04hRBk0XrYa75CLoOb5M4HROg6gncvWzuVfdu6Qs2CkMqy7ZmKsaY8PoKiBwarsKUxVMRwUokO6rR1_lergP6Q6JGvhnUnsEHNElpvJJxxjlNJUJ2Sl1x_dPJzEiYnX--H4B8zD5Mk
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Detection+of+Microdefects+in+Fabric+with+Multifarious+Patterns+and+Colors+Using+Deep+Convolutional+Neural+Network&rft.jtitle=Advances+in+polymer+technology&rft.au=Xia%2C+Rongfei&rft.au=Chen%2C+Yifei&rft.au=Ji%2C+Yangfeng&rft.date=2024-02-12&rft.issn=0730-6679&rft.eissn=1098-2329&rft.volume=2024&rft.spage=1&rft.epage=10&rft_id=info:doi/10.1155%2F2024%2F5926658&rft.externalDBID=n%2Fa&rft.externalDocID=10_1155_2024_5926658
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0730-6679&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0730-6679&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0730-6679&client=summon