当前位置: X-MOL 学术ACM Trans. Multimed. Comput. Commun. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SPGAN: Face Forgery Using Spoofing Generative Adversarial Networks
ACM Transactions on Multimedia Computing, Communications, and Applications ( IF 5.1 ) Pub Date : 2021-04-01 , DOI: 10.1145/3432817
Yidong Li 1 , Wenhua Liu 1 , Yi Jin 1 , Yuanzhouhan Cao 1
Affiliation  

Current face spoof detection schemes mainly rely on physiological cues such as eye blinking, mouth movements, and micro-expression changes, or textural attributes of the face images [9]. But none of these methods represent a viable mechanism for makeup-induced spoofing, especially since makeup has been widely used. Compared with face alteration techniques such as plastic surgery, makeup is non-permanent and cost efficient, which makes makeup-induced spoofing become a realistic threat to the integrity of a face recognition system. To solve this problem, we propose a generative model to construct spoofing face images (confusing face images) for improving the accuracy and robustness of automatic face recognition. Our network structure is composed of two separate parts, with one using inter-attention mechanism to obtain interested face region, and another using intra-attention to translate imitation style with preserving imitation style-excluding details. These two attention mechanisms can precisely learn imitation style, where inter-attention pays more attention to imitation regions of image and intra-attention learns face attributes with long distance in image. To effectively discriminate generated images, we introduce an imitation style discriminator. Our model (SPGAN) generates face images that transfer the imitation style from target to subject image and preserve the imitation-excluding features. Experimental results demonstrate the performance of our model in improving quality of imitated face images.

中文翻译:

SPGAN:使用欺骗生成对抗网络进行面部伪造

目前的人脸欺骗检测方案主要依赖于生理线索,如眨眼、嘴巴运动和微表情变化,或人脸图像的纹理属性[9]。但是这些方法都不能代表化妆诱导的欺骗的可行机制,特别是因为化妆已被广泛使用。与整形手术等面部改变技术相比,化妆是非永久性的且具有成本效益,这使得化妆诱导的欺骗成为对面部识别系统完整性的现实威胁。为了解决这个问题,我们提出了一种生成模型来构建欺骗人脸图像(混淆人脸图像),以提高自动人脸识别的准确性和鲁棒性。我们的网络结构由两个独立的部分组成,一个使用 inter-attention 机制来获取感兴趣的人脸区域,另一个使用intra-attention翻译模仿风格,保留模仿风格-排除细节。这两种注意力机制可以精确地学习模仿风格,其中inter-attention更关注图像的模仿区域,而intra-attention学习图像中距离较远的人脸属性。为了有效地区分生成的图像,我们引入了模仿风格鉴别器。我们的模型(SPGAN)生成将模仿风格从目标图像转移到主题图像并保留模仿排除特征的人脸图像。实验结果证明了我们的模型在提高模仿人脸图像质量方面的性能。其中 inter-attention 更关注图像的模仿区域,intra-attention 学习图像中距离较远的人脸属性。为了有效地区分生成的图像,我们引入了模仿风格鉴别器。我们的模型(SPGAN)生成将模仿风格从目标图像转移到主题图像并保留模仿排除特征的人脸图像。实验结果证明了我们的模型在提高模仿人脸图像质量方面的性能。其中 inter-attention 更关注图像的模仿区域,intra-attention 学习图像中距离较远的人脸属性。为了有效地区分生成的图像,我们引入了模仿风格鉴别器。我们的模型(SPGAN)生成将模仿风格从目标图像转移到主题图像并保留模仿排除特征的人脸图像。实验结果证明了我们的模型在提高模仿人脸图像质量方面的性能。我们的模型(SPGAN)生成将模仿风格从目标图像转移到主题图像并保留模仿排除特征的人脸图像。实验结果证明了我们的模型在提高模仿人脸图像质量方面的性能。我们的模型(SPGAN)生成将模仿风格从目标图像转移到主题图像并保留模仿排除特征的人脸图像。实验结果证明了我们的模型在提高模仿人脸图像质量方面的性能。
更新日期:2021-04-01
down
wechat
bug