Fake Image Detection Using An Ensemble of CNN Models Specialized For Individual Face Parts
Fake Image Detection Using An Ensemble of CNN Models Specialized For Individual Face Parts
复制标题
DOI：
10.1109/mcsoc57363.2022.00021
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Akihisa Kawabe;Ryuto Haga;Yoichi Tomioka;Y. Okuyama;Jungpil Shin
中科院分区：
文献类型：
--
作者：
Akihisa Kawabe;Ryuto Haga;Yoichi Tomioka;Y. Okuyama;Jungpil Shin
随着深度学习技术的快速发展，利用人工智能（AI）创建人脸图像变得越来越容易。这些生成的图像将成为人类无法将其与真实图像区分开来的图像。必须实现一种准确的方法来检测此类假图像以避免滥用它们。在本文中，我们提出了一种使用卷积神经网络（CNN）模型的集成模型进行假图像检测的方法，该模型专注于单个面部部位的深度伪造检测。我们的结果表明，基于不同面部部位的深度换脸检测组合是有效的。这个想法可以应用于部分操纵的深度伪造图像/视频。
With the rapid increase of deep learning technology, creating human face images with artificial intelligence (AI) is becoming easier. Those generated images are coming up to images that humans cannot distinguish from authentic ones. It is essential to realize an accurate method to detect such fake images to avoid abusing them. In this paper, we propose a fake image detection using an ensemble model of convolutional neural network (CNN) models that focus on deepfake detection of individual face parts. Our results show that a combination of deepfake detection based on different face parts is effective. This idea can be adopted on partially manipulated deepfake images/videos.