Biometric person recognition poses a very challenging pattern recognition problem because of large variability in biometric sample quality encountered during testing and a restricted number of enrollment samples for training. Furthermore, biometric traits can change over time due to aging and change of lifestyle. Effectively, the noise factors encountered in testing cannot be represented by the limited training samples. A promising solution to training data deficiency and ageing is to use an adaptive biometric system. These systems attempt to adapt themselves to follow the change in the input biometric data. Adaptive biometrics deserves a treatment on its own right because standard machine-learning algorithms cannot readily handle changing signal quality. The aim of this chapter is to introduce the concept of adaptive biometric systems in terms of taxonomy, level of adaptation, open issues and challenges involved.
CITATION STYLE
Rattani, A. (2015). Introduction to Adaptive Biometric Systems. In Advances in Computer Vision and Pattern Recognition (pp. 1–8). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-24865-3_1
Mendeley helps you to discover research relevant for your work.