A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain
This addresses the need for reliable detection of synthetic images, which is incremental as it builds on existing frequency-based methods.
The authors tackled the problem of detecting CNN-generated images by analyzing checkerboard artifacts in the frequency domain, and their ensemble method outperformed a state-of-the-art detector under certain conditions.
We propose a novel universal detector for detecting images generated by using CNNs. In this paper, properties of checkerboard artifacts in CNN-generated images are considered, and the spectrum of images is enhanced in accordance with the properties. Next, a classifier is trained by using the enhanced spectrums to judge a query image to be a CNN-generated ones or not. In addition, an ensemble of the proposed detector with emphasized spectrums and a conventional detector is proposed to improve the performance of these methods. In an experiment, the proposed ensemble is demonstrated to outperform a state-of-the-art method under some conditions.