Anomaly Detection using Deep Learning based Image Completion
This work addresses the challenge of limited labeled data in manufacturing industries by enabling unsupervised anomaly detection, though it is incremental as it builds on existing image completion techniques.
The paper tackled the problem of automated surface inspection in manufacturing by using a deep learning-based image completion method for anomaly detection, achieving superior performance over other tested methods.
Automated surface inspection is an important task in many manufacturing industries and often requires machine learning driven solutions. Supervised approaches, however, can be challenging, since it is often difficult to obtain large amounts of labeled training data. In this work, we instead perform one-class unsupervised learning on fault-free samples by training a deep convolutional neural network to complete images whose center regions are cut out. Since the network is trained exclusively on fault-free data, it completes the image patches with a fault-free version of the missing image region. The pixel-wise reconstruction error within the cut out region is an anomaly image which can be used for anomaly detection. Results on surface images of decorated plastic parts demonstrate that this approach is suitable for detection of visible anomalies and moreover surpasses all other tested methods.