The Library
Distinguishing between natural and GAN-generated face images by combining global and local features
Tools
Chen, Beijing, Tan, Weijin, Wang, Yiting and Zhao, Guoying (2022) Distinguishing between natural and GAN-generated face images by combining global and local features. Chinese Journal of Electronics, 31 (1). pp. 59-67. doi:10.1049/cje.2020.00.372 ISSN 2075-5597.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: https://doi.org/10.1049/cje.2020.00.372
Abstract
With the development of face image synthesis and generation technology based on generative adversarial networks (GANs), it has become a research hotspot to determine whether a given face image is natural or generated. However, the generalization capability of the existing algorithms is still to be improved. Therefore, this paper proposes a general algorithm. To do so, firstly, the learning on important local areas, containing many face key-points, is strengthened by combining the global and local features. Secondly, metric learning based on the ArcFace loss is applied to extract common and discriminative features. Finally, the extracted features are fed into the classification module to detect GAN-generated faces. The experiments are conducted on two publicly available natural datasets (CelebA and FFHQ) and seven GAN-generated datasets. Experimental results demonstrate that the proposed algorithm achieves a better generalization performance with an average detection accuracy over 0.99 than the state-of-the-art algorithms. Moreover, the proposed algorithm is robust against additional attacks, such as Gaussian blur, and Gaussian noise addition.
Item Type: | Journal Article | ||||
---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||
Journal or Publication Title: | Chinese Journal of Electronics | ||||
Publisher: | IET | ||||
ISSN: | 2075-5597 | ||||
Official Date: | January 2022 | ||||
Dates: |
|
||||
Volume: | 31 | ||||
Number: | 1 | ||||
Page Range: | pp. 59-67 | ||||
DOI: | 10.1049/cje.2020.00.372 | ||||
Status: | Peer Reviewed | ||||
Publication Status: | Published | ||||
Access rights to Published version: | Open Access (Creative Commons) | ||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |