ABSTRACT
One-class classification is an increasingly used classification approach in the remote sensing community. It can be used to classify one specific class and requires only labelled training data of this class of interest. Several one-class classifiers have been introduced and many comparative studies evaluate their performance. In most, if not all, of these comparisons each classifier is analysed with a specific (hyper-) parameter and threshold selection approach. In this letter, we present an ‘in-depth’ comparison of the frequently used one-class classifiers one-class Support Vector Machine (SVM), biased SVM (bSVM) and MaxEnt, that is, a frequently used maximum entropy-based technique. We create various classification tasks with eight classes of interest and three feature sets (multi-temporal RapidEye, TerraSAR-X and fused data set) and evaluate the overall performance of the two classifiers with different parameter and threshold selection approaches. Our results show that over all classification approaches bSVM outperforms one-class SVM and MaxEnt in terms of discriminative power. However, the state-of-the-art implementation of the bSVM performed relatively poor and the best results were obtained with an alternative threshold selection approach. We found that even the best overall approach still performs poor in a significant amount of tasks. Therefore, we conclude that not only more sophisticated model selection approaches should be developed but also diagnostic tools that support the user in the evaluation of a classification result in the absence of a complete and representative test set.
Acknowledgements
TerraSAR-X data was provided by DLR under the RADARSAT-2/TerraSAR-X proposal id 5049/RES0921. RapidEye data was provided from the RapidEye Science Archive (RESA) by DLR under the proposal id490. Ground truth data was made available by RPG-AGRICOLE 2011 (c) Ministère de l’Agriculture, de la Viticulture et du Développement rural, Grand Duchy of Luxembourg. We also acknowledge the comments of the reviewers, which have contributed to improving the paper.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes
1. The parameter (ocSVM) was ignored to determine the border cases since we tuned in the range (0.01, 0.9) and the possible values for this parameter are in the range 0–1.