Cargando…

Forgery Detection in Digital Images by Multi-Scale Noise Estimation

A complex processing chain is applied from the moment a raw image is acquired until the final image is obtained. This process transforms the originally Poisson-distributed noise into a complex noise model. Noise inconsistency analysis is a rich source for forgery detection, as forged regions have li...

Descripción completa

Detalles Bibliográficos
Autores principales: Gardella, Marina, Musé, Pablo, Morel, Jean-Michel, Colom, Miguel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321373/
http://dx.doi.org/10.3390/jimaging7070119
_version_ 1783730837227831296
author Gardella, Marina
Musé, Pablo
Morel, Jean-Michel
Colom, Miguel
author_facet Gardella, Marina
Musé, Pablo
Morel, Jean-Michel
Colom, Miguel
author_sort Gardella, Marina
collection PubMed
description A complex processing chain is applied from the moment a raw image is acquired until the final image is obtained. This process transforms the originally Poisson-distributed noise into a complex noise model. Noise inconsistency analysis is a rich source for forgery detection, as forged regions have likely undergone a different processing pipeline or out-camera processing. We propose a multi-scale approach, which is shown to be suitable for analyzing the highly correlated noise present in JPEG-compressed images. We estimate a noise curve for each image block, in each color channel and at each scale. We then compare each noise curve to its corresponding noise curve obtained from the whole image by counting the percentage of bins of the local noise curve that are below the global one. This procedure yields crucial detection cues since many forgeries create a local noise deficit. Our method is shown to be competitive with the state of the art. It outperforms all other methods when evaluated using the MCC score, or on forged regions large enough and for colorization attacks, regardless of the evaluation metric.
format Online
Article
Text
id pubmed-8321373
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83213732021-08-26 Forgery Detection in Digital Images by Multi-Scale Noise Estimation Gardella, Marina Musé, Pablo Morel, Jean-Michel Colom, Miguel J Imaging Article A complex processing chain is applied from the moment a raw image is acquired until the final image is obtained. This process transforms the originally Poisson-distributed noise into a complex noise model. Noise inconsistency analysis is a rich source for forgery detection, as forged regions have likely undergone a different processing pipeline or out-camera processing. We propose a multi-scale approach, which is shown to be suitable for analyzing the highly correlated noise present in JPEG-compressed images. We estimate a noise curve for each image block, in each color channel and at each scale. We then compare each noise curve to its corresponding noise curve obtained from the whole image by counting the percentage of bins of the local noise curve that are below the global one. This procedure yields crucial detection cues since many forgeries create a local noise deficit. Our method is shown to be competitive with the state of the art. It outperforms all other methods when evaluated using the MCC score, or on forged regions large enough and for colorization attacks, regardless of the evaluation metric. MDPI 2021-07-17 /pmc/articles/PMC8321373/ http://dx.doi.org/10.3390/jimaging7070119 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Gardella, Marina
Musé, Pablo
Morel, Jean-Michel
Colom, Miguel
Forgery Detection in Digital Images by Multi-Scale Noise Estimation
title Forgery Detection in Digital Images by Multi-Scale Noise Estimation
title_full Forgery Detection in Digital Images by Multi-Scale Noise Estimation
title_fullStr Forgery Detection in Digital Images by Multi-Scale Noise Estimation
title_full_unstemmed Forgery Detection in Digital Images by Multi-Scale Noise Estimation
title_short Forgery Detection in Digital Images by Multi-Scale Noise Estimation
title_sort forgery detection in digital images by multi-scale noise estimation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321373/
http://dx.doi.org/10.3390/jimaging7070119
work_keys_str_mv AT gardellamarina forgerydetectionindigitalimagesbymultiscalenoiseestimation
AT musepablo forgerydetectionindigitalimagesbymultiscalenoiseestimation
AT moreljeanmichel forgerydetectionindigitalimagesbymultiscalenoiseestimation
AT colommiguel forgerydetectionindigitalimagesbymultiscalenoiseestimation