Abstract

This is a dataset regarding the creation of forgery images. The dataset consists of 1000 original and 3000 forgery images generated from the original images. The original images have been retrieved from publicly available repositories. Three different models have been used for creating the forgery images: cut-paste, copy-move, and erase-filling. Both pre-processing (sharpening, color enhancement, resizing, blurring, regulating exposure) and post-processing (sampling, rotation, masking) techniques have been considered for the generation of the forgery images. The dataset can be used for research in the area of fake image identification. This dataset has been created in the context of the H2020 project SocialTruth.

Instructions:

• The original images are included in two different directories (low resolution and high resolution).
• There are three different sub-directories corresponding to the three different forgery models.
• In each sub-directory, there are folders associated with pre-processing and post-processing techniques.
• All post-processing techniques have been applied to forgery images.

Comments

Hello

Submitted by Md. Alamin on Sun, 01/16/2022 - 01:40

Thank you for the share

Submitted by Sahbi Baccar on Fri, 05/06/2022 - 05:34

Thank you for sharing.

Submitted by Wang yulin on Mon, 10/31/2022 - 03:34

Submitted by Hasan ABDULRAHMAN on Fri, 11/24/2023 - 18:48

Datasets

Standard Dataset

Forgery Image Dataset

Abstract

Comments

Dataset Files

QUESTIONS?