STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Image Processing & Pattern Recognition Progress

SMIFD-750: Social Media Image Forgery Detection Database

  1. Md. Mehedi Rahman Rana
  2. Abul Hasnat
  3. G. M. Atiqur Rahaman

Abstract

Forgery images or manipulated images are spreading rapidly through popular social media such as Facebook, Twitter etc. Image forgery distorts the main part and uses misinformation and hides important parts of the original images. These threats are strongly evolving that many people are being victimized by these forgery images. This is having a detrimental effect on our society. An abundant number of Image Forgery Detection (IFD) methods are available, but the benchmark for rating in real-world is limited because of the lack of diverse datasets. The aim of this research is to solve the problem by introducing a new IFD dataset, called SMIFD-750, to evaluate the competency of IFD methods. An error level analysis of each image in this dataset has been performed, which is a supreme feature of this dataset.

Keywords

Support