FIDAC- Forged Images Detection And Classification

Citation Author(s):
Sonali
Bhutad
Professor at Shah & Anchor Kutchhi Engineering College
Bhavin
Goswami
Student at Shah & Anchor Kutchhi Engineering College
Gaurangi
Pradhan
Student at Shah & Anchor Kutchhi Engineering College
Shraddha
Pawar
Student at Shah & Anchor Kutchhi Engineering College
Submitted by:
Shraddha Pawar
Last updated:
Fri, 01/14/2022 - 10:48
DOI:
10.21227/4det-6512
Data Format:
License:
5
1 rating - Please login to submit your rating.

Abstract 

This dataset consists of 2 types of images i.e Authentic and Tampered. There are a total of 1,415 Authentic images and 598 Tampered images. Authentic images are camera clicked images in raw form & tampered images are the one being edited by Adobe Photoshop. Different types of forgery techniques like copy-move, splicing, color enhancement, resizing etc have been applied on the tampered images. 

The main motive of this dataset is to optimize the AI/ML based fake image identification model. Thus, this dataset is used for the R&D of fake image classification. 

Instructions: 
  • The dataset consists of a total of 2013 images in  *.png, *.jpg, *.jpeg files formats.

  • The dataset requires a space of 100 Mb.

  • The dataset consists of two folders namely Authentic_Images & Tampered_Images.