Detection and Localization of Image Forgeries Using Resampling Features and Deep Learning

Abstract

Resampling is an important signature of manipulated images. In this paper, we propose two methods to detect and localize image manipulations based on a combination of resampling features and deep learning. In the first method, the Radon transform of resampling features are computed on overlapping image patches. Deep learning classifiers and a Gaussian conditional random field model are then used to create a heatmap. Tampered regions are located using a Random Walker segmentation method. In the second method, resampling features computed on overlapping image patches are passed through a Long short-term memory (LSTM) based network for classification and localization. We compare the performance of detection/localization of both these methods. Our experimental results show that both techniques are effective in detecting and localizing digital image forgeries.

Cite

Text

Bunk et al. "Detection and Localization of Image Forgeries Using Resampling Features and Deep Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.235

Markdown

[Bunk et al. "Detection and Localization of Image Forgeries Using Resampling Features and Deep Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/bunk2017cvprw-detection/) doi:10.1109/CVPRW.2017.235

BibTeX

@inproceedings{bunk2017cvprw-detection,
  title     = {{Detection and Localization of Image Forgeries Using Resampling Features and Deep Learning}},
  author    = {Bunk, Jason and Bappy, Jawadul H. and Mohammed, Tajuddin Manhar and Nataraj, Lakshmanan and Flenner, Arjuna and Manjunath, B. S. and Chandrasekaran, Shivkumar and Roy-Chowdhury, Amit K. and Peterson, Lawrence},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {1881-1889},
  doi       = {10.1109/CVPRW.2017.235},
  url       = {https://mlanthology.org/cvprw/2017/bunk2017cvprw-detection/}
}