TY - GEN
T1 - Forgery Detection by Internal Positional Learning of Demosaicing Traces
AU - Bammey, Quentin
AU - von Gioi, Rafael Grompone
AU - Morel, Jean-Michel
PY - 2022
Y1 - 2022
N2 - 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. Check qbammey.github.io/4point for the code. © 2022 IEEE.
AB - 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. Check qbammey.github.io/4point for the code. © 2022 IEEE.
KW - Few-shot
KW - Semi- and Un- supervised Learning Image forensics
KW - Transfer
UR - http://www.scopus.com/inward/record.url?scp=85126105174&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85126105174&origin=recordpage
U2 - 10.1109/WACV51458.2022.00109
DO - 10.1109/WACV51458.2022.00109
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781665409162
T3 - Proceedings - IEEE/CVF Winter Conference on Applications of Computer Vision, WACV
SP - 1019
EP - 1029
BT - Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
PB - IEEE
T2 - 22nd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2022)
Y2 - 4 January 2022 through 8 January 2022
ER -