Browse > Article
http://dx.doi.org/10.30693/SMJ.2022.11.11.92

A Study on the Defect Detection of Fabrics using Deep Learning  

Eun Su Nam (계명대학교 경영정보학과)
Yoon Sung Choi (다이텍연구원 소재빅데이터연구센터)
Choong Kwon Lee (계명대학교 경영정보학과)
Publication Information
Smart Media Journal / v.11, no.11, 2022 , pp. 92-98 More about this Journal
Abstract
Identifying defects in textiles is a key procedure for quality control. This study attempted to create a model that detects defects by analyzing the images of the fabrics. The models used in the study were deep learning-based VGGNet and ResNet, and the defect detection performance of the two models was compared and evaluated. The accuracy of the VGGNet and the ResNet model was 0.859 and 0.893, respectively, which showed the higher accuracy of the ResNet. In addition, the region of attention of the model was derived by using the Grad-CAM algorithm, an eXplainable Artificial Intelligence (XAI) technique, to find out the location of the region that the deep learning model recognized as a defect in the fabric image. As a result, it was confirmed that the region recognized by the deep learning model as a defect in the fabric was actually defective even with the naked eyes. The results of this study are expected to reduce the time and cost incurred in the fabric production process by utilizing deep learning-based artificial intelligence in the defect detection of the textile industry.
Keywords
fabric defects; VGGNet; ResNet; Grad-CAM;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 A. Seker, "Evaluation of Fabric Defect Detection Based on Transfer Learning with Pre-trained AlexNet," In Proceedings of the 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), pp. 1-4, Malatya, Turkey, Sep. 2018.
2 B. Wei, K. Hao, X. Tang, and Y. Ding, "A new method using the convolutional neural network with compressive sensing for fabric defect classification based on small sample sizes," Textile Research Journal, Vol. 89, No. 17, PP. 3539-3555, Dec. 2018.    DOI
3 김민재, 신종호, "전이학습을 이용한 비전기반 결함 탐지 알고리즘 개발," 한국 CDE 학회 논문집, 제23권, 제3호, 246-255쪽, 2020년 9월
4 김수빈, 이기안, "CNN 을 이용한 Al 6061 압출재의 표면 결함 분류 연구," 소성가공, 제31권, 제4호, 229-239쪽, 2022년 7월   DOI
5 서기성, "표면 결함 분류를 위한 적정 규모의 딥러닝 모델," 전기학회논문지, 제69권, 제12호, 1957-1961쪽, 2020년 12월
6 김대현, 부승빈, 홍현철, 여원구, 이남용, "딥러닝 알고리즘을 이용한 머신 비전 기반 불량 검출 연구", 비파괴검사학회지, 제40권, 제1호, 47-52쪽, 2020년 2월
7 이병우, 이우창, 채승완, 김동현, 이충권, "딥러닝 기반 이미지 특징 추출 모델을 이용한 유사 디자인 검출에 대한 연구," 스마트미디어저널, 제9권, 제4호, 162-169쪽, 2020년 12월
8 정성훈, 최형택, 홍철재, "화상처리를 응용한 직물 결점 검출 (I)," 한국섬유공학회지, 제37권, 제1호, 34-43쪽, 2000년 1월
9 조유진, 신창선, "딥러닝기반 토마토 병해 진단 서비스 연구," 스마트미디어저널, 제11권, 제5호, 48-55쪽, 2022년 6월
10 채승완, 이충권, 이병우, 이우창, "텍스타일 디자인 분류 및 관심 영역 도출에 대한 연구," 스마트미디어저널, 제10권, 제2호, 70-75쪽, 2021년 6월
11 E. Westphal, and H. Seitz, "A machine learning method for defect detection and visualization in selective laser sintering based on convolutional neural networks," Additive Manufacturing, Vol. 41, No. 101965, May, 2021.
12 X. Tao, D. Zhang, W. Ma, X. Liu, and D. Xu, "Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks," Applied Sciences, Vol. 8, No. 9, pp. 1575, Sep.
13 K. Simonyan, A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, Sep. 2014.
14 K. HE, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, Las Vegas, USA, Jun. 2016.
15 R. R., Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh and D. Batra, "Grad-cam: Visual explanations from deep networks via gradient-based localization," In Proceedings of the IEEE International Conference on Computer Vision, pp. 618-626, Venice, Italy, Oct. 2017.
16 이정범, 정다흰, 윤성로, "합성곱 신경망을 이용한 원단 결점 검출 시스템," 대한전자공학회 정기총회 및 추계학술대회, 2018. 11
17 A. Durmusoglu, and Y. Kahraman, "Detection of Fabric Defects Using Convolutional Networks," In 2021 Innovations in Intelligent Systems and Applications Conference(ASYU), pp. 1-5, Elazig, Turkey, October 2021.
18 M. Guan, Z. Zhong, Y. Rui, H. Zhen and X. Wu, "Defect detection and classification for plain woven fabric based on deep learning," In 2019 Seventh International Conference on Advanced Cloud and Big Data (CBD), pp. 297-302, Suzhou, China, Sep. 2019.