A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images

被引:15
|
作者
Cui, Yajie [1 ]
Liu, Zhaoxiang [1 ]
Lian, Shiguo [1 ]
机构
[1] Unicom Digital Technol Co Ltd, Beijing 100013, Peoples R China
关键词
Anomaly detection; Visualization; Surveys; Deep learning; Production; Filter banks; Gabor filters; Industrial anomaly detection; unsupervised learning; deep learning; DEFECT DETECTION; SURFACE-DEFECTS; FEATURE-SELECTION; CLASSIFICATION; RECOGNITION; TRANSFORM; FEATURES;
D O I
10.1109/ACCESS.2023.3282993
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In line with the development of Industry 4.0, surface defect detection/anomaly detection becomes a topical subject in the industry field. Improving efficiency as well as saving labor costs has steadily become a matter of great concern in practice, where deep learning-based algorithms perform better than traditional vision inspection methods in recent years. While existing deep learning-based algorithms are biased towards supervised learning, which not only necessitates a huge amount of labeled data and human labor, but also brings about inefficiency and limitations. In contrast, recent research shows that unsupervised learning has great potential in tackling the above disadvantages for visual industrial anomaly detection. In this survey, we summarize current challenges and provide a thorough overview of recently proposed unsupervised algorithms for visual industrial anomaly detection covering five categories, whose innovation points and frameworks are described in detail. Meanwhile, publicly available datasets for industrial anomaly detection are introduced. By comparing different classes of methods, the advantages and disadvantages of anomaly detection algorithms are summarized. Based on the current research framework, we point out the core issue that remains to be resolved and provide further improvement directions. Meanwhile, based on the latest technological trends, we offer insights into future research directions. It is expected to assist both the research community and industry in developing a broader and cross-domain perspective.
引用
收藏
页码:55297 / 55315
页数:19
相关论文
共 50 条
  • [1] Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
    Tao, Xian
    Gong, Xinyi
    Zhang, Xin
    Yan, Shaohua
    Adak, Chandranath
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [2] Ensemble Algorithms for Unsupervised Anomaly Detection
    Zhao, Zhiruo
    Mehrotra, Kishan G.
    Mohan, Chilukuri K.
    CURRENT APPROACHES IN APPLIED ARTIFICIAL INTELLIGENCE, 2015, 9101 : 514 - 525
  • [3] On Algorithms Selection for Unsupervised Anomaly Detection
    Zoppi, Tommaso
    Ceccarelli, Andrea
    Bondavalli, Andrea
    2018 IEEE 23RD PACIFIC RIM INTERNATIONAL SYMPOSIUM ON DEPENDABLE COMPUTING (PRDC), 2018, : 279 - 288
  • [4] Unsupervised Anomaly Detection of Industrial Images Based on Dual Generator Reconstruction Networks
    Gu, Cong
    Ren, Siyv
    Duan, Qiqiang
    INFORMATION TECHNOLOGY AND CONTROL, 2024, 53 (02): : 331 - 341
  • [5] Unsupervised industrial anomaly detection with diffusion models
    Xu, Haohao
    Xu, Shuchang
    Yang, Wenzhen
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 97
  • [7] A Survey On Unsupervised Change Detection Algorithms
    Venkateswaran, K.
    Kasthuri, N.
    Haran, Arathy. C., V
    Jeni, D. Dorin
    PROCEEDINGS OF 2013 INTERNATIONAL CONFERENCE ON CIRCUITS, POWER AND COMPUTING TECHNOLOGIES (ICCPCT 2013), 2013, : 897 - 903
  • [8] Quantitative Comparison of Unsupervised Anomaly Detection Algorithms for Intrusion Detection
    Falcao, Filipe
    Zoppi, Tommaso
    Viera Silva, Caio Barbosa
    Santos, Anderson
    Fonseca, Baldoino
    Ceccarelli, Andrea
    Bondavalli, Andrea
    SAC '19: PROCEEDINGS OF THE 34TH ACM/SIGAPP SYMPOSIUM ON APPLIED COMPUTING, 2019, : 318 - 327
  • [9] A Comprehensive Survey of Anomaly Detection Algorithms
    Samariya D.
    Thakkar A.
    Annals of Data Science, 2023, 10 (3) : 829 - 850
  • [10] Towards Practical Unsupervised Anomaly Detection on Retinal Images
    Ouardini, Khalil
    Yang, Huijuan
    Unnikrishnan, Balagopal
    Romain, Manon
    Garcin, Camille
    Zenati, Houssam
    Campbell, J. Peter
    Chiang, Michael F.
    Kalpathy-Cramer, Jayashree
    Chandrasekhar, Vijay
    Krishnaswamy, Pavitra
    Foo, Chuan-Sheng
    DOMAIN ADAPTATION AND REPRESENTATION TRANSFER AND MEDICAL IMAGE LEARNING WITH LESS LABELS AND IMPERFECT DATA, DART 2019, MIL3ID 2019, 2019, 11795 : 225 - 234