Abstract
Anomaly Detection (AD) has recently received considerable attention in various applications such as biometrics, computer vision, and machine learning. To detect anomalies, modelling and encapsulating normal data is still an open problem, especially if only normal (non-anomalous) data is available for training time, making it a challenging problem. In this thesis, the challenge of a pure AD design is studied using non-anomalous samples only. For that, several pure AD models are developed so that each one deals with a specific domain.
Presentation attacks (PA) are recognised as a considerable threat to biometric devices. To counteract PAs, the majority of approaches formulate the problem as a two-class classification. Nevertheless, the two-class formulation does not perform robustly due to its poor generalisation performance in the presence of novel PAs. To address this limitation, a pure AD model is trained where the real-access is considered as \textit{normal} and PAs are presumed to be \textit{anomalous} observations. An aspect of PAD design that has been overlooked is the use of client-specific information in the context of AD. As the first contribution, client-specific information is adopted to build the one-class classifiers (OCCs).
The idea of constructing a fusion of OCCs has received increasing attention. Nevertheless, very few studies in the literature have been concerned with developing a general methodology of OCC fusion design. In the thesis, it is aimed to redress this limitation by proposing a generic OCC fusion method with three novel contributions: (a) A new score normalisation method is proposed as a preprocessing step to multiple classifier fusion that can cope well with heavy-tailed non-anomalous data distributions (b) A novel fitness function is defined which requires only normal observations to estimate the competency of OCCs (c) A new pruning method is proposed to discard OCCs having no/less informative data from the fusion to improve the AD results.
Up to this point, Convolutional neural Networks (CNNs) pretrained on Imagenet have been used in the thesis to extract the features from image data. To train a CNN from scratch, a deep network is pretrained using self-supervised learning for an auxiliary geometric transformation (GT) classification task. The key contribution is a novel loss function that augments the standard cross-entropy by an additional term that plays a significant role in the later stages of self-supervised learning. The pretrained network is finetuned for the downstream task using non-anomalous data only, and a GT model for the data is constructed. Anomalies are detected by fusing the output of several decision functions defined using the learnt GT class model.
Extensive experiments on publicly available AD datasets demonstrate the effectiveness of the proposed contributions and lead to significant performance gains compared to the state-of-the-art methods. This includes benchmarking datasets in PAD, conventional tabular datasets in the machine learning domain and common computer vision.