Unsupervised UNet for Fabric Defect Detection

被引：3

作者：

Liu, Kuan-Hsien ^{[1
]}

Chen, Song-Jie ^{[1
]}

Liu, Tsung-Jung ^{[2
]}

机构：

[1] Natl Taichung Univ Sci & Technol, Taichung, Taiwan

[2] Natl Chung Hsing Univ, Taichung, Taiwan

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN, IEEE ICCE-TW 2022 | 2022年

关键词：

Fabric defect detection; image reconstruction and synthesis; residual; U-net; unsupervised learning;

D O I：

10.1109/ICCE-TAIWAN55306.2022.9869207

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Currently, neural network based defect detection systems usually need to collect a large number of defect samples for training, and it takes a lot of manpower to mark labels and clean the subsequent data. This is a time-consuming process, and it makes the whole system less effective. In this paper, a neural network based method for fabric surface defect detection is proposed. By training positive clean samples, it can learn through neural network without collecting negative defective samples, which greatly shortens the landing time of whole system. Our proposed system can achieve 99% detection accuracy.

引用

页码：205 / 206

页数：2

共 50 条

[41] Fabric defect detection in stockwell transform domain
Zhao, Cuifang, 1600, International Frequency Sensor Association (169):
[42] Fabric defect detection using morphological filters
Mak, K. L.
Peng, P.
Yiu, K. F. C.
IMAGE AND VISION COMPUTING, 2009, 27 (10) : 1585 - 1592
[43] Fabric defect detection using adaptive wavelet
Zhi, YX
Pang, GKH
Yung, NHC
2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 3697 - 3700
[44] Fabric Defect Detection Based on Texture Enhancement
Zuo, Haiqin
Wang, Yujie
Yang, Xuezhi
Wang, Xin
2012 5TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), 2012, : 876 - 880
[45] Fabric Defect Detection using Deep Learning
Seker, Abdulkadir
Peker, Kadir Askin
Yuksek, Ahmet Gurkan
Delibas, Emre
2016 24TH SIGNAL PROCESSING AND COMMUNICATION APPLICATION CONFERENCE (SIU), 2016, : 1437 - 1440
[46] In-process fabric defect detection and identification
Dorrity, JL
Vachtsevanos, GJ
MECHATRONICS '98, 1998, : 745 - 750
[47] Fabric Defect Detection Using Wavelet Decomposition
Li, Yundong
Di, Xia
2013 3RD INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, COMMUNICATIONS AND NETWORKS (CECNET), 2013, : 308 - 311
[48] Fabric Defect Detection using Wavelet Filter
Karlekar, Vaibhav V.
Biradar, M. S.
Bhangale, K. B.
1ST INTERNATIONAL CONFERENCE ON COMPUTING COMMUNICATION CONTROL AND AUTOMATION ICCUBEA 2015, 2015, : 712 - 715
[49] Fabric Defect Detection Based on Wavelet Characteristics
Guan, Shengqi
Shi, Xiuhua
Cui, Haiying
Song, Yuqin
PACIIA: 2008 PACIFIC-ASIA WORKSHOP ON COMPUTATIONAL INTELLIGENCE AND INDUSTRIAL APPLICATION, VOLS 1-3, PROCEEDINGS, 2008, : 349 - 353
[50] Data Augmentation Method For Fabric Defect Detection
Wang, Po-Hsiang
Lin, Chien-Chou
2022 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN, IEEE ICCE-TW 2022, 2022, : 255 - 256

← 1 2 3 4 5 →