Open AccessLocal accumulated smoothing patterns for fingerprint liveness detection
Author(s) -
Kim W.,
Jung C.
Publication year - 2016
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2016.3371
Subject(s) - liveness , smoothing , robustness (evolution) , artificial intelligence , computer science , fingerprint (computing) , computer vision , pattern recognition (psychology) , exploit , fingerprint recognition , process (computing) , theoretical computer science , biochemistry , chemistry , computer security , gene , operating system
A novel image descriptor for fingerprint liveness detection is presented. Inspired by the observation that textural distortions due to the fabrication process are well revealed by edge‐aware filtering, it is proposed to exploit the local patterns on the accumulated smoothing space for determining whether a given fingerprint is fake or not. Experimental results on LivDet 2009 and 2011 datasets show the efficiency and robustness of the proposed method compared with previous local image descriptors.