An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network

Y. H. Zhang; C. W.M. Yuen; Wai Keung Wong; Chi Wai Kan

doi:10.1109/IASP.2010.5476161

An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network

Y. H. Zhang, C. W.M. Yuen, Wai Keung Wong, Chi Wai Kan

The Hong Kong Polytechnic University

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

3 Citations (Scopus)

Abstract

In this paper a new knitted garment defect detection and classification model based on 2D Gabor wavelet transform and Elman neural network is introduced. A new modified Elman network is proposed to classify the type of fabric defects which have proportional (P), integral (I), derivative (D) properties. The proposed inspecting model in this study is more feasible and applicable in fabric defect detection and classification. Compared with the traditional back propagation BP network, the successful classification rate obtained by the PID Elman network is higher than the BP neural network with the same number of classification parameter, and training time and classification time used by PID Elman is less than BP neural network.

Original language	English
Title of host publication	IASP 10 - 2010 International Conference on Image Analysis and Signal Processing
Pages	69-74
Number of pages	6
DOIs	https://doi.org/10.1109/IASP.2010.5476161
Publication status	Published - 12 Jul 2010
Event	2nd International Conference on Image Analysis and Signal Processing, IASP'2010 - Xiamen, China Duration: 12 Apr 2010 → 14 Apr 2010

Conference

Conference	2nd International Conference on Image Analysis and Signal Processing, IASP'2010
Country/Territory	China
City	Xiamen
Period	12/04/10 → 14/04/10

Keywords

Classification
Elman neural network
Fabric defect detection
Gabor filter
PID

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Signal Processing

More information

10.1109/IASP.2010.5476161

Cite this

@inproceedings{1aa693134a3849328114fa7b6492e0d9,

title = "An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network",

abstract = "In this paper a new knitted garment defect detection and classification model based on 2D Gabor wavelet transform and Elman neural network is introduced. A new modified Elman network is proposed to classify the type of fabric defects which have proportional (P), integral (I), derivative (D) properties. The proposed inspecting model in this study is more feasible and applicable in fabric defect detection and classification. Compared with the traditional back propagation BP network, the successful classification rate obtained by the PID Elman network is higher than the BP neural network with the same number of classification parameter, and training time and classification time used by PID Elman is less than BP neural network.",

keywords = "Classification, Elman neural network, Fabric defect detection, Gabor filter, PID",

author = "Zhang, {Y. H.} and Yuen, {C. W.M.} and Wong, {Wai Keung} and Kan, {Chi Wai}",

year = "2010",

month = jul,

day = "12",

doi = "10.1109/IASP.2010.5476161",

language = "English",

isbn = "9781424455553",

pages = "69--74",

booktitle = "IASP 10 - 2010 International Conference on Image Analysis and Signal Processing",

note = "2nd International Conference on Image Analysis and Signal Processing, IASP'2010 ; Conference date: 12-04-2010 Through 14-04-2010",

}

Zhang, YH, Yuen, CWM, Wong, WK & Kan, CW 2010, An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network. in IASP 10 - 2010 International Conference on Image Analysis and Signal Processing., 5476161, pp. 69-74, 2nd International Conference on Image Analysis and Signal Processing, IASP'2010, Xiamen, China, 12/04/10. https://doi.org/10.1109/IASP.2010.5476161

An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network. / Zhang, Y. H.; Yuen, C. W.M.; Wong, Wai Keung et al.
IASP 10 - 2010 International Conference on Image Analysis and Signal Processing. 2010. p. 69-74 5476161.

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

TY - GEN

T1 - An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network

AU - Zhang, Y. H.

AU - Yuen, C. W.M.

AU - Wong, Wai Keung

AU - Kan, Chi Wai

PY - 2010/7/12

Y1 - 2010/7/12

N2 - In this paper a new knitted garment defect detection and classification model based on 2D Gabor wavelet transform and Elman neural network is introduced. A new modified Elman network is proposed to classify the type of fabric defects which have proportional (P), integral (I), derivative (D) properties. The proposed inspecting model in this study is more feasible and applicable in fabric defect detection and classification. Compared with the traditional back propagation BP network, the successful classification rate obtained by the PID Elman network is higher than the BP neural network with the same number of classification parameter, and training time and classification time used by PID Elman is less than BP neural network.

AB - In this paper a new knitted garment defect detection and classification model based on 2D Gabor wavelet transform and Elman neural network is introduced. A new modified Elman network is proposed to classify the type of fabric defects which have proportional (P), integral (I), derivative (D) properties. The proposed inspecting model in this study is more feasible and applicable in fabric defect detection and classification. Compared with the traditional back propagation BP network, the successful classification rate obtained by the PID Elman network is higher than the BP neural network with the same number of classification parameter, and training time and classification time used by PID Elman is less than BP neural network.

KW - Classification

KW - Elman neural network

KW - Fabric defect detection

KW - Gabor filter

KW - PID

UR - http://www.scopus.com/inward/record.url?scp=77954335763&partnerID=8YFLogxK

U2 - 10.1109/IASP.2010.5476161

DO - 10.1109/IASP.2010.5476161

M3 - Conference article published in proceeding or book

SN - 9781424455553

SP - 69

EP - 74

BT - IASP 10 - 2010 International Conference on Image Analysis and Signal Processing

T2 - 2nd International Conference on Image Analysis and Signal Processing, IASP'2010

Y2 - 12 April 2010 through 14 April 2010

ER -

An intelligent knitted garment defect detection and classification model based on gabor filter and modified Elman neural network

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this