Communication Dans Un Congrès Année : 2022

Forgery Detection by Internal Positional Learning of Demosaicing Traces

Quentin Bammey
Jean-Michel Morel

Résumé

We propose 4Point (Forensics with Positional Internal Training), an unsupervised neural network trained to assess the consistency of the image colour mosaic to find forgeries. Positional learning trains the model to learn the modulo-2 position of pixels, leveraging the translation-invariance of CNN to replicate the underlying mosaic and its potential inconsistencies. Internal learning on a single potentially forged image improves adaption and robustness to varied post-processing and counter-forensics measures. This solution beats existing mosaic detection methods, is more robust to various post-processing and counter-forensic artefacts such as JPEG compression, and can exploit traces to which state-of-the-art generic neural networks are blind.

Fichier principal
Vignette du fichier
WACV22_CFA.pdf (3.98 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03907100 , version 1 (19-12-2022)

Licence

Identifiants

Citer

Quentin Bammey, Rafael Grompone von Gioi, Jean-Michel Morel. Forgery Detection by Internal Positional Learning of Demosaicing Traces. 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2022, Waikoloa, United States. pp.1019-1029, ⟨10.1109/WACV51458.2022.00109⟩. ⟨hal-03907100⟩
153 Consultations
350 Téléchargements

Altmetric

Partager

  • More