2017/08/25 by Joshua J. Engelsma, Kai Cao, Engelsma, Joshua J. +3 · 1 voice
Computer Science · Social Sciences · #Biometric Identification and Security #Forensic Fingerprint Detection Methods
paper · pdf · doi:10.48550/arxiv.1708.07887
We present the design and prototype of an open source, optical fingerprint\nreader, called RaspiReader, using ubiquitous components. RaspiReader, a\nlow-cost and easy to assemble reader, provides the fingerprint research\ncommunity a seamless and simple method for gaining more control over the\nsensing component of fingerprint recognition systems. In particular, we posit\nthat this versatile fingerprint reader will encourage researchers to explore\nnovel spoof detection methods that integrate both hardware and software.\nRaspiReader's hardware is customized with two cameras for fingerprint\nacquisition with one camera providing high contrast, frustrated total internal\nreflection (FTIR) images, and the other camera outputting direct images. Using\nboth of these image streams, we extract complementary information which, when\nfused together, results in highly discriminative features for fingerprint spoof\n(presentation attack) detection. Our experimental results demonstrate a marked\nimprovement over previous spoof detection methods which rely only on FTIR\nimages provided by COTS optical readers. Finally, fingerprint matching\nexperiments between images acquired from the FTIR output of the RaspiReader and\nimages acquired from a COTS fingerprint reader verify the interoperability of\nthe RaspiReader with existing COTS optical readers.\n