arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.02162cs.CV
收藏

差分人脸形态检测中的条件身份解纠缠

Conditional Identity Disentanglement for Differential Face Morph Detection

Michigan State University(密歇根州立大学)

Sudipta Banerjee, Arun Ross

摘要:

我们提出了差分人脸变形攻击检测的任务,使用条件生成网络(cGAN)。为了确定身份证件(如护照)中的人脸图像是否变形,我们提出了一种算法,该算法使用cGAN学习隐式地从变形图像中分离身份,该变形图像以可信参考图像为条件。此外,所提出的方法还可以恢复用于生成变形的关于第二主体的一些潜在信息。我们在AMSL人脸变形,MorGAN和EMorGAN数据集上进行了实验,以证明所提出的方法的有效性。我们还进行了跨数据集和交叉攻击检测实验。我们在数据集内评估中获得了3%BPCER@10%APCER的令人鼓舞的结果,这与现有方法相当;在跨数据集评估中获得了4.6%BPCER@10%APCER,这比最先进的方法至少高出13.9%。

英文摘要:

We present the task of differential face morph attack detection using a conditional generative network (cGAN). To determine whether a face image in an identification document, such as a passport, is morphed or not, we propose an algorithm that learns to implicitly disentangle identities from the morphed image conditioned on the trusted reference image using the cGAN. Furthermore, the proposed method can also recover some underlying information about the second subject used in generating the morph. We performed experiments on AMSL face morph, MorGAN, and EMorGAN datasets to demonstrate the effectiveness of the proposed method. We also conducted cross-dataset and cross-attack detection experiments. We obtained promising results of 3% BPCER @ 10% APCER on intra-dataset evaluation, which is comparable to existing methods; and 4.6% BPCER @ 10% APCER on cross-dataset evaluation, which outperforms state-of-the-art methods by at least 13.9%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑