Accurate detection methods for GAN-generated earth observation images using expert visual perceptionTools Yates, Matthew (2023) Accurate detection methods for GAN-generated earth observation images using expert visual perception. PhD thesis, University of Nottingham.
AbstractImage generation techniques, such as generative adversarial networks (GANs), have become sufficiently sophisticated to cause growing security concerns regarding image authenticity. Although generation and detection methods are often applied to a range of images such as objects and faces, more domain specific image types such as Earth Observation (EO) have received relatively little attention, leaving the field vulnerable to potential malicious misuse of this technology. This thesis investigates the current state of EO specific GAN generation and detection methods using an interdisciplinary approach. This work argues that further detection methods should incorporate both human and computational detection to improve current techniques. Evidence to support this conclusion is given by the following contributions:
Actions (Archive Staff Only)
|
Tools
Tools
