https://scholars.lib.ntu.edu.tw/handle/123456789/614699
標題: | Anomaly detection neural network with dual auto-encoders GAN and its industrial inspection applications | 作者: | Tang T.-W. Kuo W.-H. Lan J.-H. CHIEN-FANG DING Hsu H. Young H.-T. |
關鍵字: | Cost reduction; Deep learning; Defects; Image reconstruction; Inspection; Learning systems; Network coding; Wages; Adversarial networks; Anomaly detection models; Areas under the curves; Automated optical inspection systems; Defective products; Detection ability; Industrial detection; Industrial inspections; Anomaly detection | 公開日期: | 2020 | 出版社: | MDPI AG | 卷: | 20 | 期: | 12 | 摘要: | Recently, researchers have been studying methods to introduce deep learning into automated optical inspection (AOI) systems to reduce labor costs. However, the integration of deep learning in the industry may encounter major challenges such as sample imbalance (defective products that only account for a small proportion). Therefore, in this study, an anomaly detection neural network, dual auto-encoder generative adversarial network (DAGAN), was developed to solve the problem of sample imbalance. With skip-connection and dual auto-encoder architecture, the proposed method exhibited excellent image reconstruction ability and training stability. Three datasets, namely public industrial detection training set, MVTec AD, with mobile phone screen glass and wood defect detection datasets, were used to verify the inspection ability of DAGAN. In addition, training with a limited amount of data was proposed to verify its detection ability. The results demonstrated that the areas under the curve (AUCs) of DAGAN were better than previous generative adversarial network-based anomaly detection models in 13 out of 17 categories in these datasets, especially in categories with high variability or noise. The maximum AUC improvement was 0.250 (toothbrush). Moreover, the proposed method exhibited better detection ability than the U-Net auto-encoder, which indicates the function of discriminator in this application. Furthermore, the proposed method had a high level of AUCs when using only a small amount of training data. DAGAN can significantly reduce the time and cost of collecting and labeling data when it is applied to industrial detection. © 2020 by the authors. Licensee MDPI, Basel, Switzerland. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086435579&doi=10.3390%2fs20123336&partnerID=40&md5=b2cf5fd23fb4a349114c89431383f052 https://scholars.lib.ntu.edu.tw/handle/123456789/614699 |
ISSN: | 14248220 | DOI: | 10.3390/s20123336 |
顯示於: | 生物機電工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。