Camera model identification based machine learning approach with high order statistics features

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 : Source camera identification methods aim at identifying the camera used to capture an image. In this paper we developed a method for digital camera model identification by extracting three sets of features in a machine learning scheme. These features are the co-occurrences matrix, some features related to CFA interpolation arrangement, and conditional probability statistics. These features give high order statistics which supplement and enhance the identification rate. The method is implemented with 14 camera models from Dresden database with multi class SVM classifier. A comparison is performed between our method and a camera fingerprint correlation-based method which only depends on PRNU extraction. The experiments prove the strength of our proposition since it achieves higher accuracy than the correlation-based method.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01374110
Contributor : Marc Chaumont <>
Submitted on : Thursday, September 29, 2016 - 5:12:49 PM
Last modification on : Thursday, May 24, 2018 - 3:59:23 PM
Long-term archiving on : Friday, December 30, 2016 - 2:51:46 PM

File

EUSIPCO-2016_TUAMA_COMBY_CHAUM...
Files produced by the author(s)

Identifiers

Collections

Citation

Amel Tuama, Frédéric Comby, Marc Chaumont. Camera model identification based machine learning approach with high order statistics features. EUSIPCO: European Signal Processing Conference, Aug 2016, Budapest, Hungary. pp.1183-1187, ⟨10.1109/EUSIPCO.2016.7760435⟩. ⟨hal-01374110⟩

Share

Metrics

Record views

221

Files downloads

526