Biometric characteristics are immutable and hence their compromise is permanent. To address this problem, cancelable biometrics was introduced to denote biometric templates that can be canceled and replaced. BioHash is a form of cancelable biometrics which mixes a set of user-specific random numbers with the biometric features. The main drawback of BioHash is its great degradation in performance when the legitimate token is stolen and used by the imposter to claim as the legitimate user. In this paper, we employ a modified probabilistic neural network as the classifier to alleviate this problem. The experiments are tested on the FERET face data set with promising results.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence