Fake Generated Painting Detection via Frequency Analysis
arXiv:2003.02467 · doi:10.1109/ICIP40778.2020.9190892
Abstract
With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms.To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts. Based on our observations, we propose Fake Generated Painting Detection via Frequency Analysis (FGPD-FA) by extracting three types of features in frequency domain. Besides, we also propose a digital fake painting detection database for assessing the proposed method. Experimental results demonstrate the excellence of the proposed method in different testing conditions.
arXiv comment5 pages, 6 figures, accepted by ICIP 2020
References in corpus (8)
- Scikit-learn: Machine Learning in Python
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Identification of Deep Network Generated Images Using Disparities in Color Components
- Fast Patch-based Style Transfer of Arbitrary Style
- Fake Colorized Image Detection
- Distinguishing Computer-generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning
- Face X-ray for More General Face Forgery Detection