Source Camera Model Identification Using Features from contaminated Sensor Noise

Amel Tuama 1 Frédéric Comby 1 Marc Chaumont 1
1 ICAR - Image & Interaction
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : This paper presents a new approach of camera model identification. It is based on using the noise residual extracted from an image by applying a wavelet-based denoising filter in a machine learning framework. We refer to this noise residual as the polluted noise (POL-PRNU), because it contains a PRNU signal contaminated with other types of noise such as the image content. Our proposition consists of extracting high order statistics from POL-PRNU by computing co-occurrences matrix. Additionally, we enrich the set of features with those related to CFA demosaicing artifacts. These two sets of features feed a classifier to perform a camera model identification. The experimental results illustrate the fact that machine learning techniques with discriminant features are efficient for camera model identification purposes.
Document type :
Conference papers
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01234164
Contributor : Marc Chaumont <>
Submitted on : Thursday, November 26, 2015 - 12:16:36 PM
Last modification on : Friday, May 3, 2019 - 2:59:39 PM
Long-term archiving on : Friday, April 28, 2017 - 11:25:11 PM

File

IWDW2015_TUAMA_COMBY_CHAUMONT_...
Files produced by the author(s)

Identifiers

Collections

Citation

Amel Tuama, Frédéric Comby, Marc Chaumont. Source Camera Model Identification Using Features from contaminated Sensor Noise. IWDW: International Workshop on Digital Watermarking, Oct 2015, Tokyo, Japan. pp.83-93, ⟨10.1007/978-3-319-31960-5_8⟩. ⟨lirmm-01234164⟩

Share

Metrics

Record views

371

Files downloads

1021