Multi-Perspective Anomaly Detection
This addresses anomaly detection for manufacturing applications using multiple image perspectives, but it is incremental as it builds on existing methods.
The paper tackles multi-perspective anomaly detection in manufacturing by extending deep support vector data description with fusion techniques and data augmentation, achieving an ROC AUC of 80% on a new dataset and outperforming single-perspective methods on MNIST and dices datasets.
Anomaly detection is a critical problem in the manufacturing industry. In many applications, images of objects to be analyzed are captured from multiple perspectives which can be exploited to improve the robustness of anomaly detection. In this work, we build upon the deep support vector data description algorithm and address multi-perspective anomaly detection using three different fusion techniques, i.e., early fusion, late fusion, and late fusion with multiple decoders. We employ different augmentation techniques with a denoising process to deal with scarce one-class data, which further improves the performance (ROC AUC $= 80\%$). Furthermore, we introduce the dices dataset, which consists of over 2000 grayscale images of falling dices from multiple perspectives, with 5\% of the images containing rare anomalies (e.g., drill holes, sawing, or scratches). We evaluate our approach on the new dices dataset using images from two different perspectives and also benchmark on the standard MNIST dataset. Extensive experiments demonstrate that our proposed {multi-perspective} approach exceeds the state-of-the-art {single-perspective anomaly detection on both the MNIST and dices datasets}. To the best of our knowledge, this is the first work that focuses on addressing multi-perspective anomaly detection in images by jointly using different perspectives together with one single objective function for anomaly detection.