Towards Fingerprint Presentation Attack Detection Based on Short Wave Infrared Imaging and Spectral Signatures
Marta Gomez‐Barrero, Jascha Kolberg, Christoph Busch · 2018
Biometric verification systems are currently being deployed in numerous large-scale andeveryday applications. Among other vulnerabilities, presentation attacks directed to thesensor (e.g., using a face mask or a gummy finger) pose a severe security threat. To preventsuch attacks, presentation attack detection (PAD) techniques have been proposed in thelast decade. For the particular case of fingerprint recognition, most approaches are basedon conventional optical or capacitive sensors, acquiring a single image, and which can thusdetect only a limited number of materials used to fool the sensor.In this paper we propose a PAD algorithm based on normalised spectral signaturesextracted from ShortWave InfraRed (SWIR) images captured at four different wavelengths.It has been shown that the information contained in the selected SWIR wavelengths canhelp to discriminate skin from other materials. The extracted features are classified usinga Support Vector Machine (SVM), thereby yielding a fast real-time performance which canbe implemented on almost any application. The experimental evaluation shows that allbut one material considered can be detected, including unknown materials (i.e., not usedto train the classifier).