Fingerphoto Presentation Attack Detection: Generalization in Smartphones
Emanuela Marasco, Anudeep Vurity
Abstract
A fingerphoto is obtained by imaging a human finger using a basic smartphone camera. Although impressive advances have been made to accurately match fingerphotos, this technology is vulnerable to presentation attacks (PAs). These algorithms do not generalize well in the presence of new presentation attacks. While previous research on this issue is limited, this paper systematically evaluates fingerphoto presentation attack detection (PAD) algorithms under unknown attacks. The proposed assessment compares different Convolutional Neural Networks (CNNs) on the IIITD Smartphone Fingerphoto database with spoof data including printout and various display attacks. These images used for the experiments were acquired indoors and subjected to background (i.e., white or natural) and capture device (i.e., Nokia or OPO) variations. Preliminary results show that the PAD based on AlexNet is robust under most types of replica unseen during the training of the detector.