A Study on Liveness Analysis for Palmprint Recognition System

This paper presents a novel liveness detection approach of hand biometrics. Liveness detection approach is applied to hand traits which are segmented with Active Appearance Model (AAM) based hand modelling. Initially, Eulerian Video Magnification (EVM) based feature extraction method is applied to segmented hand video sequences. In this step, all points in base video frame are evaluated as input. Thus, two feature vectors are extracted for one point. Afterwards, vector normalization and Discrete Fourier Transform (DFT) are separately applied to obtained feature vectors as post processing step. Thereafter, two feature vectors are concatenated to generate long feature vector. Finally, all points are classified by using distance-based classification algorithm to determine input point whether live or not. The proposed liveness detection approach is tested on 15 segmented hand videos which are captured from 5 different people in 414960 points. Sensitivity, specificity, and accuracy values are calculated to show proposed approach's success. Liveness regions of hand traits are also determined to make confident analysis in this approach.

[1]  Woo Chaw Seng,et al.  A review of biometric technology along with trends and prospects , 2014, Pattern Recognit..

[2]  Frédo Durand,et al.  Eulerian video magnification for revealing subtle changes in the world , 2012, ACM Trans. Graph..

[3]  Murat Ekinci,et al.  Developing a contactless palmprint authentication system by introducing a novel ROI extraction method , 2015, Image Vis. Comput..

[4]  Adam Czajka,et al.  Biometric verification based on hand thermal images , 2013, 2013 International Conference on Biometrics (ICB).

[5]  Gian Luca Foresti,et al.  MoBio_LivDet: Mobile biometric liveness detection , 2014, 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[6]  Bin Qin,et al.  The Anti-spoofing Study of Vein Identification System , 2009, 2009 International Conference on Computational Intelligence and Security.

[7]  Sébastien Marcel,et al.  Image Quality Assessment for Fake Biometric Detection: Application to Iris, Fingerprint, and Face Recognition , 2014, IEEE Transactions on Image Processing.