Year: 2019
Type: conference-paper
Abstract: Generative adversary networks (GANs) have recently led to highly realistic image synthesis results. In this work, we describe a new method to expose GAN-synthesized images using the locations of the facial landmark points. Our method is based on the observations that the facial parts configuration generated by GAN models are different from those of the real faces, due to the lack of global constraints. We perform experiments demonstrating this phenomenon, and show that an SVM classifier trained using the locations of facial landmark points is sufficient to achieve good classification performance for GAN-synthesized faces.
Authors: Xin Yang, Yuezun Li, Honggang Qi, Siwei Lyu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2959409678
