Feature Fusion for Blurring Detection in Image Forensics

BenJuan YANG; BenYong LIU

doi:10.1587/transinf.E97.D.1690

Feature Fusion for Blurring Detection in Image Forensics

BenJuan YANG, BenYong LIU

Full Text Views

0

Cite this

Summary :

Artificial blurring is a typical operation in image forging. Most existing image forgery detection methods consider only one single feature of artificial blurring operation. In this manuscript, we propose to adopt feature fusion, with multifeatures for artificial blurring operation in image tampering, to improve the accuracy of forgery detection. First, three feature vectors that address the singular values of the gray image matrix, correlation coefficients for double blurring operation, and image quality metrics (IQM) are extracted and fused using principal component analysis (PCA), and then a support vector machine (SVM) classifier is trained using the fused feature extracted from training images or image patches containing artificial blurring operations. Finally, the same procedures of feature extraction and feature fusion are carried out on the suspected image or suspected image patch which is then classified, using the trained SVM, into forged or non-forged classes. Experimental results show the feasibility of the proposed method for image tampering feature fusion and forgery detection.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.6 pp.1690-1693

Publication Date: 2014/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.1690

Type of Manuscript: LETTER

Category: Image Processing and Video Processing

Authors

BenJuan YANG
Guizhou University,Guizhou Normal University
BenYong LIU
Guizhou University

Keyword

image forensics, blurring detection, feature fusion, PCA, SVM

Cite this

Copy

BenJuan YANG, BenYong LIU, "Feature Fusion for Blurring Detection in Image Forensics" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 6, pp. 1690-1693, June 2014, doi: 10.1587/transinf.E97.D.1690.
Abstract: Artificial blurring is a typical operation in image forging. Most existing image forgery detection methods consider only one single feature of artificial blurring operation. In this manuscript, we propose to adopt feature fusion, with multifeatures for artificial blurring operation in image tampering, to improve the accuracy of forgery detection. First, three feature vectors that address the singular values of the gray image matrix, correlation coefficients for double blurring operation, and image quality metrics (IQM) are extracted and fused using principal component analysis (PCA), and then a support vector machine (SVM) classifier is trained using the fused feature extracted from training images or image patches containing artificial blurring operations. Finally, the same procedures of feature extraction and feature fusion are carried out on the suspected image or suspected image patch which is then classified, using the trained SVM, into forged or non-forged classes. Experimental results show the feasibility of the proposed method for image tampering feature fusion and forgery detection.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.1690/_p

Copy

@ARTICLE{e97-d_6_1690,
author={BenJuan YANG, BenYong LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Fusion for Blurring Detection in Image Forensics},
year={2014},
volume={E97-D},
number={6},
pages={1690-1693},
abstract={Artificial blurring is a typical operation in image forging. Most existing image forgery detection methods consider only one single feature of artificial blurring operation. In this manuscript, we propose to adopt feature fusion, with multifeatures for artificial blurring operation in image tampering, to improve the accuracy of forgery detection. First, three feature vectors that address the singular values of the gray image matrix, correlation coefficients for double blurring operation, and image quality metrics (IQM) are extracted and fused using principal component analysis (PCA), and then a support vector machine (SVM) classifier is trained using the fused feature extracted from training images or image patches containing artificial blurring operations. Finally, the same procedures of feature extraction and feature fusion are carried out on the suspected image or suspected image patch which is then classified, using the trained SVM, into forged or non-forged classes. Experimental results show the feasibility of the proposed method for image tampering feature fusion and forgery detection.},
keywords={},
doi={10.1587/transinf.E97.D.1690},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Feature Fusion for Blurring Detection in Image Forensics
T2 - IEICE TRANSACTIONS on Information
SP - 1690
EP - 1693
AU - BenJuan YANG
AU - BenYong LIU
PY - 2014
DO - 10.1587/transinf.E97.D.1690
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2014
AB - Artificial blurring is a typical operation in image forging. Most existing image forgery detection methods consider only one single feature of artificial blurring operation. In this manuscript, we propose to adopt feature fusion, with multifeatures for artificial blurring operation in image tampering, to improve the accuracy of forgery detection. First, three feature vectors that address the singular values of the gray image matrix, correlation coefficients for double blurring operation, and image quality metrics (IQM) are extracted and fused using principal component analysis (PCA), and then a support vector machine (SVM) classifier is trained using the fused feature extracted from training images or image patches containing artificial blurring operations. Finally, the same procedures of feature extraction and feature fusion are carried out on the suspected image or suspected image patch which is then classified, using the trained SVM, into forged or non-forged classes. Experimental results show the feasibility of the proposed method for image tampering feature fusion and forgery detection.
ER -