Industrial Anomaly Detection with Skip Autoencoder and Deep Feature Extractor
Author:
Tang Ta-Wei, Hsu Hakiem, Huang Wei-Ren, Li Kuan-MingORCID
Abstract
Over recent years, with the advances in image recognition technology for deep learning, researchers have devoted continued efforts toward importing anomaly detection technology into the production line of automatic optical detection. Although unsupervised learning helps overcome the high costs associated with labeling, the accuracy of anomaly detection still needs to be improved. Accordingly, this paper proposes a novel deep learning model for anomaly detection to overcome this bottleneck. Leveraging a powerful pre-trained feature extractor and the skip connection, the proposed method achieves better feature extraction and image reconstructing capabilities. Results reveal that the areas under the curve (AUC) for the proposed method are higher than those of previous anomaly detection models for 16 out of 17 categories. This indicates that the proposed method can realize the most appropriate adjustments to the needs of production lines in order to maximize economic benefits.
Funder
National Science and Technology Council, Taiwan.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference31 articles.
1. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated Residual Transformations for Deep Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. 2. Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., and Feng, J. (2017). Dual Path Networks. arXiv. 3. Tan, M., and Le, Q. (2019, January 9–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA. 4. Avdelidis, N.P., Tsourdos, A., Lafiosca, P., Plaster, R., Plaster, A., and Droznika, M. (2022). Defects Recognition Algorithm Development from Visual UAV Inspections. Sensors, 22. 5. Huang, Y., and Xiang, Z. (2022). RPDNet: Automatic Fabric Defect Detection Based on a Convolutional Neural Network and Repeated Pattern Analysis. Sensors, 22.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|