Noisesniffer: A Fully Automatic Image Forgery Detector Based on Noise Analysis

Marina GARDELLA; Pablo MUSE; Jean Michel MOREL; Miguel COLOM

doi:10.1109/IWBF50991.2021.9465095

Noisesniffer: A Fully Automatic Image Forgery Detector Based on Noise Analysis

Marina GARDELLA, Pablo MUSE, Jean Michel MOREL^*, Miguel COLOM

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

18 Citations (Scopus)

Abstract

Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of these operations leave traces on the noise model which enable forgery detection through noise analysis. In this article we define a background stochastic model which makes it possible to detect local noise anomalies characterized by their number of false alarms. The proposed method is both automatic and blind, allowing quantitative and subjectivity-free detections. Results show that the proposed method outperforms the state of the art.

Original language	English
Title of host publication	Proceedings: 9th International Workshop on Biometrics and Forensics, IWBF 2021
Publisher	IEEE
ISBN (Electronic)	9781728195568
ISBN (Print)	9781728195575
DOIs	https://doi.org/10.1109/IWBF50991.2021.9465095
Publication status	Published - 2021
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

This work was supported by a grant from Région Ile-de-France.

Keywords

automatic forgery detection
blind algorithm
image forensics
noise residual

Access to Document

10.1109/IWBF50991.2021.9465095

Cite this

@inproceedings{c52cd179f949453089992c4eda837731,

title = "Noisesniffer: A Fully Automatic Image Forgery Detector Based on Noise Analysis",

abstract = "Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of these operations leave traces on the noise model which enable forgery detection through noise analysis. In this article we define a background stochastic model which makes it possible to detect local noise anomalies characterized by their number of false alarms. The proposed method is both automatic and blind, allowing quantitative and subjectivity-free detections. Results show that the proposed method outperforms the state of the art.",

keywords = "automatic forgery detection, blind algorithm, image forensics, noise residual",

author = "Marina GARDELLA and Pablo MUSE and MOREL, \{Jean Michel\} and Miguel COLOM",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.",

year = "2021",

doi = "10.1109/IWBF50991.2021.9465095",

language = "English",

isbn = "9781728195575",

booktitle = "Proceedings: 9th International Workshop on Biometrics and Forensics, IWBF 2021",

publisher = "IEEE",

}

TY - GEN

T1 - Noisesniffer: A Fully Automatic Image Forgery Detector Based on Noise Analysis

AU - GARDELLA, Marina

AU - MUSE, Pablo

AU - MOREL, Jean Michel

AU - COLOM, Miguel

PY - 2021

Y1 - 2021

N2 - Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of these operations leave traces on the noise model which enable forgery detection through noise analysis. In this article we define a background stochastic model which makes it possible to detect local noise anomalies characterized by their number of false alarms. The proposed method is both automatic and blind, allowing quantitative and subjectivity-free detections. Results show that the proposed method outperforms the state of the art.

AB - Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of these operations leave traces on the noise model which enable forgery detection through noise analysis. In this article we define a background stochastic model which makes it possible to detect local noise anomalies characterized by their number of false alarms. The proposed method is both automatic and blind, allowing quantitative and subjectivity-free detections. Results show that the proposed method outperforms the state of the art.

KW - automatic forgery detection

KW - blind algorithm

KW - image forensics

KW - noise residual

UR - https://www.scopus.com/pages/publications/85113890060

U2 - 10.1109/IWBF50991.2021.9465095

DO - 10.1109/IWBF50991.2021.9465095

M3 - Conference paper (refereed)

AN - SCOPUS:85113890060

SN - 9781728195575

BT - Proceedings: 9th International Workshop on Biometrics and Forensics, IWBF 2021

PB - IEEE

ER -

Noisesniffer: A Fully Automatic Image Forgery Detector Based on Noise Analysis

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this