Proposal of unsupervised defect segmentation method for patterned textiles based on machine learning

被引:0
|
作者
Honda M. [1 ]
Hirosawa S. [1 ]
Mimura M. [2 ]
Hayami T. [2 ]
Kitaguchi S. [2 ]
Satou T. [2 ]
机构
[1] Kyoto Municipal Institute of Industrial Technology and Culture, 91 Chudoji Awata-Cho, Shimogyo-ku, Kyoto
[2] Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto
关键词
Defect detection; Neural networks; Textiles; Traditional crafts industries; Unsupervised machine learning;
D O I
10.4188/jte.66.47
中图分类号
学科分类号
摘要
In this paper, we propose a convolutional autoencoder with a new structure for unsupervised learning when the purity of the training data is not guaranteed. This autoencoder has two unique features: the target area is reconstructed from the surrounding areas and the L2 loss is predicted simultaneously. The superiority of this model was verified using SEM images of defective nanofibrous materials by calculating the AUC value. The results of our experiments with the training data contaminated by defective data show that the former feature improves the robustness against contamination of the training data and the latter improves the accuracy. Although this approach did not achieve the highest accuracy, it could reduce the cost of annotation for practical use. Furthermore, we applied our method to images of NISHIJIN textiles and found that it worked well for some types of textiles. © 2020 The Textile Machinery Society of Japan.
引用
收藏
页码:47 / 54
页数:7
相关论文
共 50 条
  • [1] Customer Segmentation Based on RFM Analysis and Unsupervised Machine Learning Technique
    Hallishma, Lourth
    ADVANCED NETWORK TECHNOLOGIES AND INTELLIGENT COMPUTING, ANTIC 2022, PT II, 2023, 1798 : 46 - 55
  • [2] Fabric Defect Segmentation Method Based on Deep Learning
    Huang, Yanqing
    Jing, Junfeng
    Wang, Zhen
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
  • [3] Channel head extraction based on fuzzy unsupervised machine learning method
    Wu, Jian
    Liu, Haixing
    Wang, Zhe
    Ye, Lei
    Li, Min
    Peng, Yong
    Zhang, Chi
    Zhou, Huicheng
    GEOMORPHOLOGY, 2021, 391
  • [4] Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning
    Kuric, Ivan
    Klarak, Jaromir
    Saga, Milan
    Cisar, Miroslav
    Hajducik, Adrian
    Wiecek, Dariusz
    SENSORS, 2021, 21 (21)
  • [5] Nonparametric segmentation methods: Applications of unsupervised machine learning and revealed preference
    Blumberg, Joey
    Thompson, Gary
    AMERICAN JOURNAL OF AGRICULTURAL ECONOMICS, 2022, 104 (03) : 976 - 998
  • [6] An unsupervised machine learning method for discovering patient clusters based on genetic signatures
    Lopez, Christian
    Tucker, Scott
    Salameh, Tarik
    Tucker, Conrad
    JOURNAL OF BIOMEDICAL INFORMATICS, 2018, 85 : 30 - 39
  • [7] Cylindrical secondary battery defect detection method based on unsupervised deep-learning
    Han H.-G.
    Kim H.-Y.
    Cho J.-S.
    Journal of Institute of Control, Robotics and Systems, 2021, 27 (08) : 510 - 517
  • [8] Defect Detection Method of Trash Trap Based on Deep Learning Semantic Segmentation
    Meng, Wei
    Kang, Jun-feng
    Zhou, Cun-lu
    Liu, Xiao-lin
    Wang, Shuai
    Tian, Hui-hui
    Wang, Xiang-wen
    Du, Jun
    2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 2711 - 2714
  • [9] Using Unsupervised Machine Learning Techniques for Behavioral-based Credit Card Users Segmentation in Africa
    Umuhoza, Eric
    Ntirushwamaboko, Dominique
    Awuah, Jane
    Birir, Beatrice
    SAIEE AFRICA RESEARCH JOURNAL, 2020, 111 (03): : 95 - 101
  • [10] Unsupervised Machine Learning for Automatic Image Segmentation of Impact Damage in CFRP Composites
    Zhupanska, Olesya
    Krokhmal, Pavlo
    APPLIED COMPOSITE MATERIALS, 2024, : 1849 - 1867