Loading

Geometrical Attack Classification using DCNN and Forgery Localization using Machine Learning
Abhishek Thakur1, Neeru Jindal2

1Abhishek Thakur, Department of Electronics and Communication, Thapar Institute of Engineering and Information Technology, Patiala (Punjab), India.
2Neeru Jindal, Department of Electronics and Communication, Thapar Institute of Engineering and Information Technology, Patiala (Punjab), India.
Manuscript received on 08 February 2019 | Revised Manuscript received on 21 February 2019 | Manuscript Published on 04 March 2019 | PP: 397-401 | Volume-7 Issue-5S2 January 2019 | Retrieval Number: ES2072017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Manipulation of images is frequently happening nowadays for false propaganda and also for illegal advantage. Only the manipulation of images are not sufficient as an evidence. These are considered only after valuable forensic investigation. The most common forgeries are copy move and splicing. It is very important to detect the realness of digital images which cause a grave threat to the society. This paper is about copy move, splicing forgery classification of various geometrical attacks. The deep convolution neural network is used to classify images into forged or not forged and also classify which type of forgery is present.
Keywords: Image Forensics (IF), Deep Learning (DL), Convolution Neural Network (CNN), Color Illumination (CI), Copy-move Forgery (CMF), Splicing Forgery (SF).
Scope of the Article: Machine Learning