Differential Morph Face Detection using Discriminative Wavelet Sub-bands
Differential Morph Face Detection using Discriminative Wavelet Sub-bands
复制标题
DOI：
10.1109/cvprw53098.2021.00158
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Baaria Chaudhary;Poorya Aghdaie;Sobhan Soleymani;J. Dawson;N. Nasrabadi
中科院分区：
文献类型：
--
作者：
Baaria Chaudhary;Poorya Aghdaie;Sobhan Soleymani;J. Dawson;N. Nasrabadi
人脸识别系统极易受到变形攻击，其中变形的面部参考图像可以成功地验证为两个或多个不同的身份。在本文中，我们提出了一种变形攻击检测算法，该算法利用未消差的二维离散小波变换（DWT）来识别变形的人脸图像。我们的框架的核心是，变形过程中产生的在图像域中无法识别的伪影可以在空间频率域中更容易识别。判别小波子带可以突出真实图像和变形图像之间的差异。为此，将多级DWT应用于所有图像，每个图像产生48个中频和高频子带。对于真实图像和变形图像，分别计算每个子带的熵分布。对于某些子带，真实图像中的子带熵与变形图像中的相同子带熵之间存在显著差异。因此，我们采用Kullback-Liebler散度（KLD）来利用这些差异，并分离出最具判别性的子带。我们通过KLD值来衡量子带的判别性，并选择KLD值最高的22个子带进行网络训练。然后，我们使用这22个选择的子带训练一个深度暹罗神经网络，用于差分形态攻击检测。我们研究了鉴别小波子带在形态攻击检测中的有效性，并表明在这些子带上训练的深度神经网络可以准确地识别形态图像。
Face recognition systems are extremely vulnerable to morphing attacks, in which a morphed facial reference image can be successfully verified as two or more distinct identities. In this paper, we propose a morph attack detection algorithm that leverages an undecimated 2D Discrete Wavelet Transform (DWT) for identifying morphed face images. The core of our framework is that artifacts resulting from the morphing process that are not discernible in the image domain can be more easily identified in the spatial frequency domain. A discriminative wavelet sub-band can accentuate the disparity between a real and a morphed image. To this end, multi-level DWT is applied to all images, yielding 48 mid and high-frequency sub-bands each. The entropy distributions for each sub-band are calculated separately for both bona fide and morph images. For some of the sub-bands, there is a marked difference between the entropy of the sub-band in a bona fide image and the identical sub-band’s entropy in a morphed image. Consequently, we employ Kullback-Liebler Divergence (KLD) to exploit these differences and isolate the sub-bands that are the most discriminative. We measure how discriminative a sub-band is by its KLD value and the 22 sub-bands with the highest KLD values are chosen for network training. Then, we train a deep Siamese neural network using these 22 selected sub-bands for differential morph attack detection. We examine the efficacy of discriminative wavelet sub-bands for morph attack detection and show that a deep neural network trained on these sub-bands can accurately identify morph imagery.