Open Access

ARTICLE

Copy Move Forgery Detection Using Novel Quadsort Moth Flame Light Gradient Boosting Machine

by R. Dhanya^1,*, R. Kalaiselvi²

1 Department of Computer Applications, Noorul Islam Centre for Higher Education, Nagercoil, 629180, India
2 Department of Computer Science Engineering, Noorul Islam Centre for Higher Education, Nagercoil, 629180, India

* Corresponding Author: R. Dhanya. Email:

Computer Systems Science and Engineering 2023, 45(2), 1577-1593. https://doi.org/10.32604/csse.2023.031319

Received 14 April 2022; Accepted 08 June 2022; Issue published 03 November 2022

Abstract

A severe problem in modern information systems is Digital media tampering along with fake information. Even though there is an enhancement in image development, image forgery, either by the photographer or via image manipulations, is also done in parallel. Numerous researches have been concentrated on how to identify such manipulated media or information manually along with automatically; thus conquering the complicated forgery methodologies with effortlessly obtainable technologically enhanced instruments. However, high complexity affects the developed methods. Presently, it is complicated to resolve the issue of the speed-accuracy trade-off. For tackling these challenges, this article put forward a quick and effective Copy-Move Forgery Detection (CMFD) system utilizing a novel Quad-sort Moth Flame (QMF) Light Gradient Boosting Machine (QMF-Light GBM). Utilizing Borel Transform (BT)-based Wiener Filter (BWF) and resizing, the input images are initially pre-processed by eliminating the noise in the proposed system. After that, by utilizing the Orientation Preserving Simple Linear Iterative Clustering (OPSLIC), the pre-processed images, partitioned into a number of grids, are segmented. Next, as of the segmented images, the significant features are extracted along with the feature’s distance is calculated and matched with the input images. Next, utilizing the Union Topological Measure of Pattern Diversity (UTMOPD) method, the false positive matches that took place throughout the matching process are eliminated. After that, utilizing the QMF-Light GBM visualization, the visualization of forged in conjunction with non-forged images is performed. The extensive experiments revealed that concerning detection accuracy, the proposed system could be extremely precise when contrasted to some top-notch approaches.

---

Keywords

---