An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics
Abstract
Automatically finding suspicious regions in a potentially forged image by splicing, inpainting or copy-move remains a widely open problem. Blind detection neural networks trained on benchmark data are flourishing. Yet, these methods do not provide an explanation of their detections. The more traditional methods try to provide such evidence by pointing out local inconsistencies in the image noise, JPEG compression, chromatic aberration, or in the mosaic. In this paper we develop a blind method that can train directly on unlabelled and potentially forged images to point out local mosaic inconsistencies. To this aim we designed a CNN structure inspired from demosaicing algorithms and directed at classifying image blocks by their position in the image modulo (2 x 2). Creating a diversified benchmark database using varied demosaicing methods, we explore the efficiency of the method and its ability to adapt quickly to any new data.
Cite
Text
Bammey et al. "An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.01420Markdown
[Bammey et al. "An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/bammey2020cvpr-adaptive/) doi:10.1109/CVPR42600.2020.01420BibTeX
@inproceedings{bammey2020cvpr-adaptive,
title = {{An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics}},
author = {Bammey, Quentin and von Gioi, Rafael Grompone and Morel, Jean-Michel},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2020},
doi = {10.1109/CVPR42600.2020.01420},
url = {https://mlanthology.org/cvpr/2020/bammey2020cvpr-adaptive/}
}