Topological Data Analysis for Image Forgery Detection

Authors

  • Ahmed K. Al-Jaberi1 , Aras Asaad2, Sabah A. Jassim3 , Naseer Al-Jawad4

DOI:

https://doi.org/10.37506/ijfmt.v14i3.10668

Keywords:

Image forgery. Image inpainting. Topological Data Analysis. Local Binary patterns. kNN classifier.

Abstract

The manipulation of digital images has become easy due to powerful computers, advanced photo-editing

software packages and high-resolution image-capturing devices. The identification of image authenticity

has received much attention because of the increasing power of image editing methods. Object removal is

an image forgery technique, which is usually achieved by the Exemplar-Based Inpainting (EBI) method

without any noticeable traces. Some legal issues may arise when a tampered image cannot be distinguished

from a real one by visual examination. Therefore the manipulation of digital images has become a huge

challenge to passive image forensics. There are a lot of forgery techniques that use to detect on these images

after removing the object, but these techniques have limitations when used some post-processing operations

such as super-resolution processing, noise addition, blurring and compression processes. To address this

issue, this paper proposes a novel forgery detection technique to recognize tampered inpainting images,

using topological data analysis (TDA) approach. TDA is a mathematical approach concern studying shapes

or objects to gain information about connectivity and closeness property of those objects. This proposed

technique is applied for a large number of natural images with getting a good results.

Author Biography

  • Ahmed K. Al-Jaberi1 , Aras Asaad2, Sabah A. Jassim3 , Naseer Al-Jawad4

    1Senior Lecturer, Mathematics department, college of education for pure science, the University of Basrah,

    2 Lecturer, 3 Prof and Head, 4 Senior Lecturer, School of Computing, the University of Buckingham, UK.

Downloads

Published

2020-07-30

How to Cite

Topological Data Analysis for Image Forgery Detection. (2020). Indian Journal of Forensic Medicine & Toxicology, 14(3), 1745-1751. https://doi.org/10.37506/ijfmt.v14i3.10668