General-purpose image forensics using patch likelihood under image statistical models

Wei Fan 1 Kai Wang 2 François Cayre 1
1 GIPSA-CICS - CICS
GIPSA-DIS - Département Images et Signal
2 GIPSA-AGPIG - AGPIG
GIPSA-DIS - Département Images et Signal
Abstract : This paper proposes a new, conceptually simple and effective forensic method to address both the generality and the fine-grained tampering localization problems of image forensics. Corresponding to each kind of image operation, a rich GMM (Gaussian Mixture Model) is learned as the image statistical model for small image patches. Thereafter, the binary classification problem, whether a given image block has been previously processed, can be solved by comparing the average patch log-likelihood values calculated on overlapping image patches under different GMMs of original and processed images. With comparisons to a powerful steganalytic feature, experimental results demonstrate the efficiency of the proposed method, for multiple image operations, on whole images and small blocks.
Type de document :
Communication dans un congrès
7th IEEE International Workshop on Information Forensics and Security (WIFS 2015), Nov 2015, Rome, Italy. 6 p., 2015, 〈http://www.wifs2015.org/〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01240755
Contributeur : Kai Wang <>
Soumis le : mercredi 9 décembre 2015 - 15:10:42
Dernière modification le : samedi 16 mars 2019 - 01:58:23

Identifiants

  • HAL Id : hal-01240755, version 1

Collections

Citation

Wei Fan, Kai Wang, François Cayre. General-purpose image forensics using patch likelihood under image statistical models. 7th IEEE International Workshop on Information Forensics and Security (WIFS 2015), Nov 2015, Rome, Italy. 6 p., 2015, 〈http://www.wifs2015.org/〉. 〈hal-01240755〉

Partager

Métriques

Consultations de la notice

266