Support Vector Data Description

TL;DR: Improvements to existing non-linear techniques are investigated for the purposes of providing better, timely class separation and improved anomaly detection on various multivariate datasets, culminating in application to anomaly detection in hyperspectral imagery.

TL;DR: Extensive experimental results on mainstream texture defect datasets demonstrate that ACDN achieves the state-of-the-art texture defect inspection accuracy.

TL;DR: The proposed strategy reduces the false positive rate and increases the accuracy of detecting instances from novel classes and uses two parallel hyperplanes to learn the normal region of the decision scores of the target class.

TL;DR: It is shown, that using one-class support vector machines can give as good results as canonical multi-class classifiers, while allowing to deal with imbalanced distribution and unexpected noise in the data.