Detection of presentation attacks using imaging and liveness attributes

Abstract

Face biometry is a popular user authentication scheme that is easy to use and tends to be less invasive than other user authentication approaches. Despite the success achieved by face biometrics, face spoofing attacks (or presentation attacks) still pose a challenge to researchers. In practice, fraudsters may deceive a face authentication system by displaying fake copies of an authorised user face, such as photos or videos, and gain unauthorised access to the system. This work proposes a method for detecting unauthorised access attempts using misrepresentations of the identity of an authorised user. The proposed methodology for presentation attack detection relies on the observation of imaging and liveness attributes, such as the detection of liveness using the face deformation energy, and imaging attributes usually found in authentic accesses such as facial and background textures, and steganalysis features. Based on the experimental results, the proposed approach potentially can detect face spoofing attacks at each frame of video sequences with error rates of half total error rate (HTER)= {6.51, 4.93}%, and also in full video sequences with HTER = {5.55, 0}%, for the CASIA and Nanjing University of Aeronautics and Astronautics databases, respectively.

A survey on face presentation attack detection mechanisms: hitherto and future perspectives

“…FAR denotes the false acceptance rate and FRR is used for representing false rejection rate. ‘S’ is the face anti-spoofing dataset whereas the value of equal error rate (EER) is estimated on ‘P [ 32 , 33 , 37 , 42 , 60 , 63 , 65 – 71 , 73 , 76 , 79 – 82 , 84 – 86 , 98 , 99 , 110 , 111 , 118 , 121 – 123 , 125 – 127 , 129 , 132 , 135 , 135 , 139 , 141 , 147 , 160 ] EER At certain threshold when FAR = FRR The point where error rates are equal. Commonly FMR and FNMR are compared.…”

“…Commonly FMR and FNMR are compared. In the field of PAD, BPCER and APCER are utilized instead [ 32 , 33 , 38 , 42 , 52 , 54 , 58 , 59 , 64 – 67 , 73 , 75 , 76 , 79 , 80 , 82 , 84 – 86 , 97 , 99 , 105 , 109 , 110 , 118 , 125 – 127 , 135 , 140 , 141 , 160 ] TPR The proportion of samples correctly predicted among the positive samples [ 52 , 52 , 58 , 59 , 76 , 80 ] FPR Among the negative instances, the proportion of samples correctly predicted [ 52 , 160 ] FRR FAR = ×100 FRR is the rate at which genuine users are considered as imposter by the biometric system [ 33 , 38 – 40 , 51 , 52 <...…”

“…However, authors claim the effectiveness of the proposed method, but extensive experimental results on more number of publicly available datasets may have supported the outcome. Schardosim et al [ 73 ] designed another PAD technique using facial deformation energy and other attributes, i.e., background and face textures with steganalysis features. Recently, Du et al [ 74 ] deployed residual color texture representation and proposed a novel CM texture-based descriptor that exhibit better performance compared to LPQ or LBP.…”

“…The inherent inconsistencies and variations during capturing the face images are induced mainly due to illumination effect, lightning condition, head movement, rotational, and scalar inconsistencies. However, to overcome these issues a variety of techniques have been proposed by various authors using image descriptors such as LBP ([ 32 , 58 , 64 , 68 , 73 – 75 , 83 , 99 ]) LPQ + LBP + HOG ([ 59 , 61 , 78 ]), LBP + BSIF ([ 62 ]), BSIF + LPQ + COLABP + SID and LBP ([ 65 ]), but these solutions perform well in constrained environment. Whereas, some of these descriptors offer robust feature sets for better classification accuracy but sometimes their results are not up to mark due to image variations.…”

A Contemporary Survey of Multimodal Presentation Attack Detection Techniques: Challenges and Opportunities

“…To differentiate between genuine and fake faces support vector machine was used. Schardosim et al [35] have been proposed a method that integrates the imaging features with liveness features and used to distinguish between real access and spoofing attacks. These are based on the models learned by an artificial neural network.…”