Comparison Score Fusion Towards an Optimal Alignment for Enhancing Cancelable Iris Biometrics

Abstract

Technologies of cancelable biometrics protect bio- metric data by applying transforms to biometric signals which provide a comparison of biometric templates in the transformed domain. Approaches to cancelable biometrics entail a significant decrease in recognition accuracy, i.e. applied feature transforms highly effect biometric feature extractors and comparators. In the presented work cancelable iris biometric systems operating in image domain are investigated. Sequences of comparison scores obtained during the process of feature alignment are combined in various fusion scenarios. As a result recognition accuracy is significantly improved, eliminating the inevitable decrease in accuracy caused by cancelable transforms, i.e. the proposed approach enables an operation of cancelable iris biometric systems at a high security level.