Skip to main content

Datasets

Standard Dataset

Forgery Image Dataset

Tag image
Citation Author(s):
Faria Hossain (London South Bank University)
Asim Gul (London South Bank University)
Rameez Raja (London South Bank University)
Tasos Dagiuklas (London South Bank University)
Chathura Galkandage (London South Bank University)
Submitted by:
Faria Hossain
Last updated:
DOI:
10.21227/9dmj-yn86
Data Format:
Image files
Links:
Forgery Image Directory
7602 views
Categories:
Keywords:
Fake Image
Forgery
Average: 5 (1 vote)
ACCESS DATASET CITE SHARE/EMBED

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.

Dataset Files

LOGIN TO ACCESS DATASET FILES

QUESTIONS?