Industrial Anomaly Detection with Skip Autoencoder and Deep Feature Extractor
Journal
Sensors
Journal Volume
22
Journal Issue
23
Date Issued
2022-12-01
Author(s)
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.
Subjects
anomaly detection | deep learning | feature extraction | industrial defect detection
SDGs
Publisher
MDPI
Type
journal article