Tampering detection and localization in images from social networks: A CBIR approach

Cédric Maigrot 1 Ewa Kijak 1 Ronan Sicre 1 Vincent Claveau 1
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA_D6 - MEDIA ET INTERACTIONS
Abstract : Verifying the authenticity of an image on social networks is crucial to limit the dissemination of false information. In this paper, we propose a system that provides information about tampering localization on such images, in order to help either the user or automatic methods to discriminate truth from falsehood. These images may be subjected to a large number of possible forgeries, which calls for the use of generic methods. Image forensics methods based on local features proved to be effective for the specific case of copy-move forgery. By taking advantage of the number of images available on the internet, we propose a generic system based on image retrieval, followed by image comparison based on local features to localize any kind of tampering in images from social networks. We also propose a large and challenging adapted database of real case images for evaluation
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01623105
Contributor : Cédric Maigrot <>
Submitted on : Wednesday, October 25, 2017 - 9:11:49 AM
Last modification on : Monday, February 11, 2019 - 3:17:22 PM
Document(s) archivé(s) le : Friday, January 26, 2018 - 12:28:35 PM

File

ICIAP17_forensics.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01623105, version 1

Citation

Cédric Maigrot, Ewa Kijak, Ronan Sicre, Vincent Claveau. Tampering detection and localization in images from social networks: A CBIR approach. ICIAP 2017 - International Conference on Image Analysis and Processing, Sep 2017, Catane, Italy. pp.1-11. ⟨hal-01623105⟩

Share

Metrics

Record views

499

Files downloads

460