Open AccessWavelet‐Markov local descriptor for detecting fake fingerprints
Author(s) -
Gragnaniello D.,
Poggi G.,
Sansone C.,
Verdoliva L.
Publication year - 2014
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2013.4044
Subject(s) - pattern recognition (psychology) , wavelet , artificial intelligence , computer science , liveness , markov chain , support vector machine , classifier (uml) , hidden markov model , biometrics , fingerprint (computing) , machine learning , theoretical computer science
The use of a wavelet‐Markov local descriptor, which exploits joint dependencies among wavelet coefficients, for fingerprint liveness detection, is proposed. On the LivDet 2009 datasets, a properly trained support vector machine classifier based on this descriptor guarantees an average error below 3%, as opposed to the 8% average error of the best conventional techniques.