PROJECT TITLE :

An Investigation of Local Descriptors for Biometric Spoofing Detection

ABSTRACT:

Biometric authentication systems are quite vulnerable to sophisticated spoofing attacks. To keep a sensible level of security, reliable spoofing detection tools are necessary, ideally implemented as software modules. The research in this field is very active, with local descriptors, based mostly on the analysis of microtextural features, gaining a lot of and a lot of popularity, as a result of of their glorious performance and flexibility. This paper aims at assessing the potential of those descriptors for the liveness detection task in authentication systems based on varied biometric traits: fingerprint, iris, and face. Besides compact descriptors primarily based on the freelance quantization of features, already considered for some liveness detection tasks, we tend to can study promising descriptors primarily based on the joint quantization of made native options. The experimental analysis, conducted on publicly out there data sets and in fully reproducible modality, confirms the potential of these tools for biometric applications, and points out possible lines of development toward more improvements.