Tampering Detection and Localization Through Clustering of Camera-Based CNN Features
Abstract
Due to the rapid proliferation of image capturing devices and user-friendly editing software suites, image manipulation is at everyone's hand. For this reason, the forensic community has developed a series of techniques to determine image authenticity. In this paper, we propose an algorithm for image tampering detection and localization, leveraging characteristic footprints left on images by different camera models. The rationale behind our algorithm is that all pixels of pristine images should be detected as being shot with a single device. Conversely, if a picture is obtained through image composition, traces of multiple devices can be detected. The proposed algorithm exploits a convolutional neural network (CNN) to extract characteristic camera model features from image patches. These features are then analyzed by means of iterative clustering techniques in order to detect whether an image has been forged, and localize the alien region.
Cite
Text
Bondi et al. "Tampering Detection and Localization Through Clustering of Camera-Based CNN Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.232Markdown
[Bondi et al. "Tampering Detection and Localization Through Clustering of Camera-Based CNN Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/bondi2017cvprw-tampering/) doi:10.1109/CVPRW.2017.232BibTeX
@inproceedings{bondi2017cvprw-tampering,
title = {{Tampering Detection and Localization Through Clustering of Camera-Based CNN Features}},
author = {Bondi, Luca and Lameri, Silvia and Guera, David and Bestagini, Paolo and Delp, Edward J. and Tubaro, Stefano},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {1855-1864},
doi = {10.1109/CVPRW.2017.232},
url = {https://mlanthology.org/cvprw/2017/bondi2017cvprw-tampering/}
}