High security fingerprint verification by perceptron-based fusion of multiple matchers

TitleHigh security fingerprint verification by perceptron-based fusion of multiple matchers
Publication TypeConference Paper
Year of Publication2004
AuthorsMarcialis, GL, Roli, F
EditorF. Windeatt, R;JKittler
Conference Name5th International Workshop on Multiple Classifiers Systems (MCS04)
Volume3077
Pagination364-373
Date Published09/06/2004
PublisherSpringer
Conference LocationCagliari (Italy)
Keywordsbio02, biometrics
Abstract

Recent works about perceptron-based fusion of multiple fingerprint matchers showed the effectiveness of such approach in improving the performance of personal identity verification systems. However, to the best of our knowledge, no previous work investigated such fusion approach when stringent requirements in terms of verification errors are given, and the number of available samples for perceptron training is small. Such investigation can allow to understand for which kind of applications such fusion rule can be useful. Reported experiments, based on two benchmark data sets, show that perceptron-based fusion can be useful for high security fingerprint verification applications, and it is effective in small-sample-size realistic cases.

Citation Key 182