Fake Face Images Detection and Identification of Celebrities Based on Semantic Segmentation
Fake Face Images Detection and Identification of Celebrities Based on Semantic Segmentation
复制标题
DOI：
10.1109/lsp.2022.3205481
复制
发表时间：
2022
影响因子：
3.9
通讯作者：
Renying Wang;Zhen Yang-;Weike You;Linna Zhou;Beilin Chu
中科院分区：
文献类型：
--
作者：
Renying Wang;Zhen Yang-;Weike You;Linna Zhou;Beilin Chu
基于卷积神经网络（CNN）的检测器在人脸操作检测中表现良好，但仍然受到冗余信息的限制。一些方法主要是通过融合边界来定位操作区域，丢弃一部分无用的信息，如图像背景。但这些方法仍然包含欺骗性信息，如没有纹理的面部区域，这会占用资源并影响检测精度。此外，这些方法遗漏了一些对识别有用的特征。因此，本文提出了一个模块，通过进行语义面具，以引导检测器集中在人脸。语义分割模板集中于头发、眼睛等重要区域的人脸特征，能够提供有效的人脸识别高层语义特征。我们的方法使用面具作为基于注意力的数据增强模块，并且对于许多DeepFake检测模型来说很容易集成。在多个检测器上的实验表明了该模块的有效性。在不修改其结构设计的情况下，我们的方法使基于CNN的检测器能够更好地执行。特别地，我们的方法非常适合于保护感兴趣的人免受面部伪造。
Convolutional Neural Networks (CNN) based detectors perform well in face manipulation detection, but are still limited by redundant information. Some methods focus on blending boundary to localize manipulation regions, discarding a part of useless information like background of image. But these methods still contain deceptive information such as facial regions without texture, which occupies resources and affects detection accuracy. Besides, these methods left out some features useful for identification. Therefore, this paper proposes a module by conducting semantic masks to guide detectors focus on face. The semantic segmentation masks focus on the facial features such as hair, eyes and other important areas, which can offer effective face identification high level semantic features. Our method uses masks as an attention-based data augmentation module and is simple for many DeepFake detection models to integrate. Experiments on multiple detectors with and without our module show our module's effectiveness. Without modifying their structural design, our approach enables CNN-based detectors to perform better. Especially, our method is well-suited for protecting the person of interest against face forgery.