Detection of Copy-Scale-Move Forgery in Digital Images Using SFOP and MROGH

Social network platforms such as Twitter, Instagram and Facebook are one of the fastest and most convenient means for sharing digital images. Digital images are generally accepted as credible news but, it may undergo some manipulations before being shared

  • PDF / 6,104,450 Bytes
  • 9 Pages / 439.37 x 666.142 pts Page_size
  • 22 Downloads / 239 Views

DOWNLOAD

REPORT


School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150080, China ma7moud [email protected], {qi.han,zhanghongli}@hit.edu.cn 2 Department of Mathematics, Faculty of Science, Menoufia University, Shebin El-koom 32511, Egypt

Abstract. Social network platforms such as Twitter, Instagram and Facebook are one of the fastest and most convenient means for sharing digital images. Digital images are generally accepted as credible news but, it may undergo some manipulations before being shared without leaving any obvious traces of tampering; due to existence of the powerful image editing softwares. Copy-move forgery technique is a very simple and common type of image forgery, where a part of the image is copied and then pasted in the same image to replicate or hide some parts from the image. In this paper, we proposed a copy-scale-move forgery detection method based on Scale Invariant Feature Operator (SFOP) detector. The keypoints are then described using MROGH descriptor. Experimental results show that the proposed method is able to locate and detect the forgery even if under some geometric transformations such as scaling. Keywords: Image forensics · Copy-move · Forgery detection invariant feature · RANSAC · MROGH descriptor

1

·

Scale

Introduction

Due to the existence of highly sophisticated software for editing the digital images, it became easily modify images without leaving any subtle traces. Copymove forgery technique is the most commonly used technique where, a part of the image is copied and then pasting it into another part in the same image. Therefore, Copy-move forgery detection (CMFD) algorithms aims at detecting the same or similar regions in the forged images. Figure 1 shows an example of Copy-move forgery, where the pocket of the child’s shirt is copied from his left hand side and then pasted into the other side of the shirt. Some postprocessing operations can be performed on the forged images after Copy-move operation, which makes the task of forgery detection more harder. Typically, post-processing operations are applied to cover up the forgery such as geometric transformation (e.g. scaling). Several researchers have introduced algorithms for detecting image copymove forgery which can be found in these surveys [1,6]. Generally, these methods can be classified into two main categories: block-based methods [14] and c Springer Science+Business Media Singapore 2016  W. Che et al. (Eds.): ICYCSEE 2016, Part I, CCIS 623, pp. 326–334, 2016. DOI: 10.1007/978-981-10-2053-7 29

Detection of Copy-Scale-Move Forgery in Digital Images

(a) Original image

(b) Forged image

327

(c) Detection results with the proposed method

Fig. 1. Copy-move forgery example

keypoint-based methods [2]. Due to the limitations of block-based methods especially in the robustness against scaling manipulations and time complexity, keypoint-based methods attract many researcher’s attention. Keypoint-based methods detect keypoints and then use the local features to identify duplicated regions instead of using