Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising
share
Due to the diversity of attack materials, fingerprint recognition systems (AFRSs) are vulnerable to malicious attacks. It is of great importance to propose effective Fingerprint Presentation Attack Detection (PAD) methods for the safety and reliability of AFRSs. However, current PAD methods often have poor robustness under new attack materials or sensor settings. This paper thus proposes a novel Channel-wise Feature Denoising fingerprint PAD (CFD-PAD) method by considering handling the redundant "noise" information which ignored in previous works. The proposed method learned important features of fingerprint images by weighting the importance of each channel and finding those discriminative channels and "noise" channels. Then, the propagation of "noise" channels is suppressed in the feature map to reduce interference. Specifically, a PA-Adaption loss is designed to constrain the feature distribution so as to make the feature distribution of live fingerprints more aggregate and spoof fingerprints more disperse. Our experimental results evaluated on LivDet 2017 showed that our proposed CFD-PAD can achieve 2.53 and 93.83 (TDR@FDR=1 ACE (2.53 proves the effectiveness of the proposed method. Although we have achieved a comparable result compared with the state-of-the-art multiple model based method, there still achieves an increase of TDR@FDR=1 our method. Besides, our model is simpler, lighter and, more efficient and has achieved a 74.76 state-of-the-art multiple model based method. Code will be publicly available.
READ FULL TEXT