Learning to recognise : a study on one-class classification and active learning

The thesis treats classification problems which are undersampled or where there exist an unbalance between classes in the sampling. The thesis is divided into three parts. The first two parts treat the problem of one-class classification. In the one-class classification problem, it is assumed that only examples of one of the classes, the target class, are available. The fact that no (or almost no) examples of other classes are available makes the one-class classification an example of an extremely unbalance problem. Therefore, such problem can not be described accurately by existing multi-class classifiers. However, a need to solve such classification rises from many theoretical and practical problems, e.g. the concept learning, machine fault detection and face recognition. In the third part of the thesis, we treat classification problems which are undersampled but not necessary unbalanced. In such problems, additional examples or additional knowledge about data available during training significantly improves classification performance. We investigate two types of enhancement of a small training set with additional knowledge from a large unlabelled data set: active learning and semi-supervised sampling.