A survey on industrial image anomaly detection: methods, benchmarks and rethinks

被引：0
作者：
Mao, Yu [1 ]
Chen, Ziyang [1 ]
Liu, Ying [1 ]
Dong, Cong [2 ]
Song, Kechen [1 ]
机构：
[1] Northeastern Univ, Sch Mech Engn & Automat, Shenyang 110819, Peoples R China
[2] Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Liaoning, Peoples R China
来源：
MEASUREMENT | 2025年 / 256卷
关键词：
Industrial image anomaly detection; Supervised learning; Semi-supervised learning; Unsupervised learning; Deep reinforcement learning; NETWORK;
D O I：
10.1016/j.measurement.2025.118377
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
Industrial image anomaly detection has been fully developed in recent years. After the end of the epidemic, it has received wide attention and made many new breakthroughs in industrial manufacturing fields such as automobiles, semiconductors and electronic products. This paper combines more than 200 documents, systematically reviews the development of supervised learning, semi-supervised learning, unsupervised learning and deep reinforcement learning in industrial image anomaly detection, analyzes in detail their application in actual industrial scenarios, and summarizes the relevant data sets and evaluation indicators. At the same time, this paper shows some cutting-edge technological breakthroughs in this field, deeply analyzes the challenges and discusses the potential direction of technical improvement in the future, in order to provide reference for follow-up research and promote the development of industrial image anomaly detection technology.
引用
收藏
页数：57
相关论文
共 252 条
[1]  
Abdulhafedh A., 2022, Open Access Library Journal, V9, P1, DOI DOI 10.4236/OALIB.1108414
[2]   A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Trees [J].
Aboah, Armstrong ;
Shoman, Maged ;
Mandal, Vishal ;
Davami, Sayedomidreza ;
Adu-Gyamfi, Yaw ;
Sharma, Anuj .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, :4202-4207
[3]   Adaptive Consistency Regularization for Semi-Supervised Transfer Learning [J].
Abuduweili, Abulikemu ;
Li, Xingjian ;
Shi, Humphrey ;
Xu, Cheng-Zhong ;
Dou, Dejing .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :6919-6928
[4]   An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning [J].
Aljameel, Sumayh S. ;
Alomari, Dorieh M. ;
Alismail, Shatha ;
Khawaher, Fatimah ;
Alkhudhair, Aljawharah A. ;
Aljubran, Fatimah ;
Alzannan, Razan M. .
COMPUTATION, 2022, 10 (08)
[5]   Few-shot anomaly detection using positive unlabeled learning with cycle consistency and co-occurrence features [J].
An, Sion ;
Kim, Jaehong ;
Kim, Soopil ;
Chikontwe, Philip ;
Jung, Jiwook ;
Jeon, Hyejeong ;
Park, Sang Hyun .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 256
[6]   Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning [J].
Arazo, Eric ;
Ortego, Diego ;
Albert, Paul ;
O'Connor, Noel E. ;
McGuinness, Kevin .
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[7]   Spatial pseudo-labeling for semi-supervised facies classification [J].
Asghar, Saleem ;
Choi, Junhwan ;
Yoon, Daeung ;
Byun, Joongmoo .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2020, 195
[8]   Evaluation of image processing technique as an expert system in mulberry fruit grading based on ripeness level using artificial neural networks (ANNs) and support vector machine (SVM) [J].
Azarmdel, Hossein ;
Jahanbakhshi, Ahmad ;
Mohtasebi, Seyed Saeid ;
Rosado Munoz, Alfredo .
POSTHARVEST BIOLOGY AND TECHNOLOGY, 2020, 166
[9]   Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey [J].
Bai, Qiang ;
Li, Shaobo ;
Yang, Jing ;
Song, Qisong ;
Li, Zhiang ;
Zhang, Xingxing .
IEEE ACCESS, 2020, 8 :181855-181879
[10]  
Bai Yuhu, 2024, 2024 China Automation Congress (CAC), P4162, DOI 10.1109/CAC63892.2024.10865319
12345678910