arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.04537cs.CV
收藏

使用基于分块的方法对遮挡图像进行Deepfake检测

Deepfake Detection of Occluded Images Using a Patch-based Approach

Shahid Beheshti University(沙希德·贝赫什提大学)

Mahsa Soleimani, Ali Nazari, Mohsen Ebrahimi Moghaddam

AI总结:

本研究提出一种基于整脸和人脸分块的三路径决策深度学习方法,用于检测存在遮挡的Deepfake图像,新构建数据集实验表明该方法在早期周期表现更优,并将SoTA结果提升了0.4%-7.9%。

摘要:

DeepFake涉及使用深度学习和人工智能技术来制作或更改通常由GAN生成的视频和图像内容。此外,它可能被滥用并导致虚假新闻、伦理和金融犯罪,同时也影响面部识别系统的性能。因此,检测真实或伪造图像具有重要意义,特别是为了验证人们图像或视频的原创性。该主题中最重要的挑战之一是遮挡,它会降低系统精度。在本研究中,我们提出了一种深度学习方法,使用整张人脸和人脸分块来区分存在遮挡情况下的真实/伪造图像,采用三路径决策:首先是整脸推理,其次是基于人脸分块特征向量拼接的决策,第三是基于这些特征的多数投票决策。为了测试我们的方法,创建了包括真实和伪造图像的新数据集。为了生成伪造图像,StyleGAN和StyleGAN2由FFHQ图像训练,同时StarGAN和PGGAN由CelebA图像训练。CelebA和FFHQ数据集被用作真实图像。所提出的方法在早期周期中比其他方法取得了更高的结果,并在不同构建的数据集中将SoTA结果提高了0.4%-7.9%。此外,我们在实验结果中表明,对分块进行加权可能会提高准确性。

英文摘要:

DeepFake involves the use of deep learning and artificial intelligence techniques to produce or change video and image contents typically generated by GANs. Moreover, it can be misused and leads to fictitious news, ethical and financial crimes, and also affects the performance of facial recognition systems. Thus, detection of real or fake images is significant specially to authenticate originality of people's images or videos. One of the most important challenges in this topic is obstruction that decreases the system precision. In this study, we present a deep learning approach using the entire face and face patches to distinguish real/fake images in the presence of obstruction with a three-path decision: first entire-face reasoning, second a decision based on the concatenation of feature vectors of face patches, and third a majority vote decision based on these features. To test our approach, new datasets including real and fake images are created. For producing fake images, StyleGAN and StyleGAN2 are trained by FFHQ images and also StarGAN and PGGAN are trained by CelebA images. The CelebA and FFHQ datasets are used as real images. The proposed approach reaches higher results in early epochs than other methods and increases the SoTA results by 0.4\%-7.9\% in the different built data-sets. Also, we have shown in experimental results that weighing the patches may improve accuracy.

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。

↑