Skip to content

Latest commit

 

History

History
95 lines (68 loc) · 5.39 KB

README.md

File metadata and controls

95 lines (68 loc) · 5.39 KB
Raw

Multi-patch Aggregation Models for Resampling Detection

The project is the official implementation of our IEEE ICASSP paper, "Multi-patch Aggregation Models for Resampling Detection"
— Mohit Lamba, Kaushik Mitra

The arXiv version of the paper can found at arXiv.org.

Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale well for images of varying dimensions. However, in our experiments, we observed that many state-of-the-art forensic algorithms are sensitive to image size and their performance quickly degenerates when operated on images of diverse dimensions despite re-training them using multiple image sizes. To handle this issue, we propose a novel pooling strategy called Iterative Pooling. This pooling strategy can dynamically adjust input tensors of different size and shapes without much loss of information as in ROI Max-pooling. This pooling strategy can be used with any of the existing deep models and for demonstration purposes, we show its utility on Resnet-18 for the case of resampling detection a fundamental operation for any image sought of image manipulation. Compared to existing strategies and Max-pooling it gives up to 7-8% improvement on public datasets.

The project has been summarised in the following video.

Watch the project Video

Sample Output

Image Resolution after Resampling Patch Size
< 1024x1024 128x128
~ 1024x1024 but < 2000x2000 256x256
>2000x2000 512x512

Original Image size: 512x512
Patch size: 128x128
Resampling Factor : Correctly classified images / Total test images
0.6:968/1001 0.8:976/1001 1:961/1001 1.2:935/1001 1.4:936/1001

Original Image size: 1024x1024
Patch size: 128x128
Resampling Factor : Correctly classified images / Total test images
0.6:979/1001

Original Image size: 1024x1024
Patch size: 256x256
Resampling Factor : Correctly classified images / Total test images
0.8:989/1001 1:995/1001 1.2:997/1001 1.4:952/1001

Original Image size: greater than 1024x1024
Patch size: 256x256
Resampling Factor : Correctly classified images / Total test images
0.6:991/1001 0.8:959/1001

Original Image size: greater than 1024x1024
Patch size: 512x512
Resampling Factor : Correctly classified images / Total test images
1:994/1001 1.2:963/1001 1.4:999/1001

How to use the code?

  • We provide the jupyter file containing the test code with all the dependencies in a single file. For reference the file is pre-computed with results.
  • However for running it on your own system you need to download the test dataset containing 15000 images and model checkpoint.

It should run well for Pytorch>=1.00 and torchvision>=0.2.

The Dataset

  • To run the jupyter file you just need test data containing 15,000 images.
  • However if you wish to download the full JPEG+Resampling+JPEG dataset which is over a 100GB, use this link
  • The complete dataset has 75,000 training images; 15,000 validation images and another 15,000 images for testing.
  • For each set the images are equally divided into 5 resampling factors namely - 0.6,0.8,1,1.2 and 1.4. In its current version the dataset consists of images of 5 different resolutions 512×512, 1024×1024, 3008×2000, 4288×2848 and 4928×3264.
  • This is charachteristicly distinct from recent works that evaluate on images of fixed resolution — mostly of VGA resolution. Refer Table 1 in the main paper.

Our code does not uses the validation dataset during the training phase and so the validation dataset can also be used for evaluation. We additionally provide a MATLAB file which illustrates how this dataste was created for image resolution of 1024x1024 and also describes how to add rotation to create JPEG+Roation+Resampling+JPEG manipulation dataste which is much harder case to deal with.

Cite us

If you find any information provided here useful please cite us,

  @inproceedings{lamba2020multi,
  title={multi-patch aggregation models for resampling detection},
  author={Lamba, Mohit and Mitra, Kaushik},
  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={2967--2971},
  year={2020},
  organization={IEEE}
}

Mohit Lamba and Kaushik Mitra. "Multi-Patch Aggregation Models for Resampling Detection." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.
}