DEFACTO: Image and Face Manipulation Dataset

Gael Mahfoudi (1) , Badr Tajini (2) , Florent Retraint (1) , Frederic Morain-Nicolier (3) , Jean-Luc Dugelay (2) , Marc Pic

1 LM2S - Laboratoire Modélisation et Sûreté des Systèmes
2 EURECOM
3 CRESTIC - Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804

This paper presents a novel dataset for image and face manipulation detection and localization called DEFACTO. The dataset was automatically generated using Microsoft common object in context database (MSCOCO) to produce semantically meaningful forgeries. Four categories of forgeries have been generated. Splicing forgeries which consist of inserting an external element into an image, copy-move forgeries where an element within an image is duplicated, object removal forgeries where objects are removed from images and lastly morphing where two images are warped and blended together. Over 200000 images have been generated and each image is accompanied by several annotations allowing precise localization of the forgery and information about the tampering process.

Keywords: Image Forensics; Copy-Move; Splicing; Inpainting; Object-Removal; Face Morphing; Face-Swapping

Domains: Signal and Image processing

Gael Mahfoudi, Badr Tajini, Florent Retraint, Frederic Morain-Nicolier, Jean-Luc Dugelay, et al.. DEFACTO: Image and Face Manipulation Dataset. European Signal Processing Conference (EUSIPCO), 2019, A Coruna, Spain. ⟨10.23919/EUSIPCO.2019.8903181⟩. ⟨hal-02373490⟩