Weakly Supervised Adaptation to Re-sizing for Image Manipulation Detection on Small Patches

Ludovic Darmet 1, 2 Kai Wang 1 François Cayre 2
1 GIPSA-AGPIG - AGPIG
GIPSA-DIS - Département Images et Signal
2 GIPSA-CICS - CICS
GIPSA-DIS - Département Images et Signal
Abstract : Basic image processing operations like median filtering and Gaussian blurring in general do not change the semantic content of an image, although they are commonly used to cover fingerprints of falsi-fication that does alter image content such as copy-move and splicing. Therefore image forensics researchers are interested in detecting these basic operations. Some existing detectors track local inconsistencies in statistics of the image. However these statistics are very sensitive to image development process. Thus pre-processing operations can be damaging for performances of such detectors. In this paper, we focus on a very common pre-processing operation, i.e., re-sizing, and study how it affects performance when trying to detect several image processing operations on small patches, with Gaussian Mixture Model (GMM) as feature extractor and a Dense Neural Network (DNN) as classifier. We first show performance drops. We then introduce an adaptation method which relies on better fit to testing data for the feature extraction and fine-tuning for the neural network classifier. Experimental results show that our method is able to improve results with very few labeled testing samples. We also present comparisons with an improved version of a recent CNN(Convolutional Neural Network)-based method.
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02335866
Contributor : Ludovic Darmet <>
Submitted on : Monday, October 28, 2019 - 3:06:24 PM
Last modification on : Tuesday, November 12, 2019 - 9:23:37 AM

File

IWDW2019_id31.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02335866, version 1

Collections

Citation

Ludovic Darmet, Kai Wang, François Cayre. Weakly Supervised Adaptation to Re-sizing for Image Manipulation Detection on Small Patches. 18th International Workshop on Digital-forensics and Watermarking, Nov 2019, Chengdu, China. ⟨hal-02335866⟩

Share

Metrics

Record views

14

Files downloads

15