TY - JOUR
T1 - Copy move image forgery detection based on Polar Fourier representation
AU - Wang, Yitian
AU - Kamata, Sei Ichiro
N1 - Funding Information:
Manuscript received January 13, 2018; revised April 7, 2018. This work was partially supported by JSPS KAKENHI Grant Number 15K00248.
Publisher Copyright:
© 2018, International Association of Computer Science and Information Technology.
PY - 2018/4/1
Y1 - 2018/4/1
N2 - With the rapid development of multimedia technology, it's easy for someone to obtain an image and edit it according to their own preferences or some ulterior purpose. Copy-Move is a common type of digital image forgery where a part of the original image is copied and pasted at another position in the same image. In this paper, we propose an efficient methodology for enhancing block matching based on Copy-Move forgery detection. The main contribution of this work is the utilization of polar representation to get the representative features for each block. The main feature used in this paper is the frequency of each block based on Fourier transform. The experimental results show the efficiency of the proposed method for detecting copy-move regions, even when the copied region has undergone severe image manipulations such as rotation, scaling, Gaussian blurring, brightness modification, JPEG compression and noise addition.
AB - With the rapid development of multimedia technology, it's easy for someone to obtain an image and edit it according to their own preferences or some ulterior purpose. Copy-Move is a common type of digital image forgery where a part of the original image is copied and pasted at another position in the same image. In this paper, we propose an efficient methodology for enhancing block matching based on Copy-Move forgery detection. The main contribution of this work is the utilization of polar representation to get the representative features for each block. The main feature used in this paper is the frequency of each block based on Fourier transform. The experimental results show the efficiency of the proposed method for detecting copy-move regions, even when the copied region has undergone severe image manipulations such as rotation, scaling, Gaussian blurring, brightness modification, JPEG compression and noise addition.
KW - Copy move
KW - Forgery detection
KW - Fourier transform
KW - Polar coordinate system
UR - http://www.scopus.com/inward/record.url?scp=85047747227&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047747227&partnerID=8YFLogxK
U2 - 10.18178/ijmlc.2018.8.2.680
DO - 10.18178/ijmlc.2018.8.2.680
M3 - Article
AN - SCOPUS:85047747227
SN - 2010-3700
VL - 8
SP - 158
EP - 163
JO - International Journal of Machine Learning and Computing
JF - International Journal of Machine Learning and Computing
IS - 2
ER -