DF-Net: The Digital Forensics Network for Image Forgery Detection

David Fischinger (Autor:in und Vortragende:r), Martin Boyer

Publikation: Beitrag in Buch oder TagungsbandVortrag mit Beitrag in TagungsbandBegutachtung

169 Downloads (Pure)

Abstract

The orchestrated manipulation of public opinion, particularly through manipulated images, often spread via online social networks (OSN), has become a serious threat to society. In this paper we introduce the Digital Forensics Net (DF-Net), a deep neural network for pixel-wise image forgery detection. The released model outperforms several state-of-the-art methods on four established benchmark datasets. Most notably, DF-Net’s detection is robust against lossy image operations (e.g resizing, compression) as they are automatically performed by social networks.
OriginalspracheEnglisch
TitelDF-Net: The Digital Forensics Network for Image Forgery Detection
Redakteure/-innenPeter Corcoran
Erscheinungsorthttps://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf
Seiten120-127
Seitenumfang8
PublikationsstatusVeröffentlicht - 2023
Veranstaltung25th Irish Machine Vision and Image Processing Conference - Galway, Ireland, Galway, Irland
Dauer: 30 Aug. 20231 Sept. 2023
https://www.universityofgalway.ie/c3i/news-&-events/imvip_2023/

Konferenz

Konferenz25th Irish Machine Vision and Image Processing Conference
KurztitelIMVIP 2023
Land/GebietIrland
StadtGalway
Zeitraum30/08/231/09/23
Internetadresse

Research Field

  • Computer Vision

Fingerprint

Untersuchen Sie die Forschungsthemen von „DF-Net: The Digital Forensics Network for Image Forgery Detection“. Zusammen bilden sie einen einzigartigen Fingerprint.

Diese Publikation zitieren