DEFACTO : Image and Face Manipulation Dataset

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

https://hal-utt.archives-ouvertes.fr/hal-02295874
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Tuesday, September 24, 2019 - 3:21:12 PM
Last modification on : Wednesday, September 25, 2019 - 10:35:29 AM

Identifiers

  • HAL Id : hal-02295874, version 1

Collections

Citation

Gaël Mahfoudi, Badr Tajini, Florent Retraint, Frederic Morain-Nicolier, Jean-Luc Dugelay, et al.. DEFACTO : Image and Face Manipulation Dataset. EUSIPCO 2019, 27th European Signal Processing Conference, Sep 2019, Coruna, Spain. ⟨hal-02295874⟩

Share

Metrics

Record views

28