Can Liveness Be Automatically Detected from Latent Fingerprints?

Fingerprint liveness detection has been widely discussed as a solution for addressing the vulnerability of fingerprint recognition systems to presentation attacks. Multiple algorithms have been designed and implemented to operate on images acquired with commercial sensors, but such methodology is not currently available for latent prints. The possibility of wrongful conviction from fake latent evidence is reasonable, since spoof finger marks can be realistically planted at a crime scene. This paper discusses concerns pertaining to spoofing friction ridges with the purpose of leaving fake marks to contaminate the evidence associated with the investigation of a crime. There is no prior literature on liveness detection from latent prints acquired from crime scene. We illustrate the need to address such threat by experimentally evaluating the existing liveness detection approaches on latent fingerprints. This study allow us to gain a deeper understanding of the advantages and disadvantages of the existing methods, and presents a novel research direction focused on investigating the effectiveness of existing countermeasures against the danger of spoofed marks. In particular, we evaluate texture-based detectors initially developed for automatic fingerprint systems and deep convolution neural networks. The experiments are carried out on the NIST SD27 latent fingerprints database.