Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
Volume 32, Issue 6, Pages 3527-3538Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3116679
Keywords
Faces; Feature extraction; Image color analysis; Convolution; Face detection; Robustness; Convolutional neural networks; Generated face; generative adversarial network; Xception; color space
Categories
Funding
- National Natural Science Foundation of China [62072251, U20B2065, 61972206]
- Natural Science Foundation of Jiangsu Province [BK20211539]
- Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD) fund
Ask authors/readers for more resources
This paper presents experimental findings on detecting post-processed GAN-generated face images and proposes a new method to improve detection performance and robustness.
In recent years, generative adversarial networks (GANs) have been widely used to generate realistic fake face images, which can easily deceive human beings. To detect these images, some methods have been proposed. However, their detection performance will be degraded greatly when the testing samples are post-processed. In this paper, some experimental studies on detecting post-processed GAN-generated face images find that (a) both the luminance component and chrominance components play an important role, and (b) the RGB and YCbCr color spaces achieve better performance than the HSV and Lab color spaces. Therefore, to enhance the robustness, both the luminance component and chrominance components of dual-color spaces (RGB and YCbCr) are considered to utilize color information effectively. In addition, the convolutional block attention module and multilayer feature aggregation module are introduced into the Xception model to enhance its feature representation power and aggregate multilayer features, respectively. Finally, a robust dual-stream network is designed by integrating dual-color spaces RGB and YCbCr and using an improved Xception model. Experimental results demonstrate that our method outperforms some existing methods, especially in its robustness against different types of post-processing operations, such as JPEG compression, Gaussian blurring, gamma correction, and median filtering.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available