Biometric antispoofing on mobile devices
In the present chapter, after a thorough review of state-of-the-art in biometric antispoofing, we present a software-based spoof detection prototype for mobile devices, named MoBio_LivDet (Mobile Biometric Liveness Detection) that can be used in multiple biometric systems. MoBio_LivDet analyzes local features and global structures of face, iris and fingerprint biometric images using a set of low-level feature descriptors and decision-level fusion. In particular, we propose to use image descriptor classification algorithms Locally Uniform Comparison Image Descriptor (LUCID) [15], CENsus TRansform hISTogram (CENTRIST) [16] and Patterns of Oriented Edge Magnitudes (POEM) [17] for face, iris and fingerprint spoof detection. The proposed system allows user to choose “Security Level” (SL) against spoofing, between “low,” “medium“ and “high.” Depending on SL, the system selects unitdescriptor or multidescriptors-fusion-based liveness detection. These descriptors are computationally inexpensive, fast and novel approach to real-time image description, which are desirable requisites for mobile processors. Experiments on publicly available data sets containing several real and spoofed faces, irises and fingerprints show promising results.
Biometric antispoofing on mobile devices, Page 1 of 2
< Previous page Next page > /docserver/preview/fulltext/books/sc/pbse003e/PBSE003E_ch15-1.gif /docserver/preview/fulltext/books/sc/pbse003e/PBSE003E_ch15-2.gif