Exposing image forgery by detecting traces of feather operation

Jiangbin Zheng, Tingge Zhu, Zhe Li, Weiwei Xing, Jinchang Ren

Research output: Contribution to journalSpecial issue

2 Citations (Scopus)
67 Downloads (Pure)

Abstract

Powerful digital image editing tools make it very easy to produce a perfect image forgery. The feather operation is necessary when tampering an image by copy–paste operation because it can help the boundary of pasted object to blend smoothly and unobtrusively with its surroundings. We propose a blind technique capable of detecting traces of feather operation to expose image forgeries. We model the feather operation, and the pixels of feather region will present similarity in their gradient phase angle and feather radius. An effectual scheme is designed to estimate each feather region pixel׳s gradient phase angle and feather radius, and the pixel׳s similarity to its neighbor pixels is defined and used to distinguish the feathered pixels from un-feathered pixels. The degree of image credibility is defined, and it is more acceptable to evaluate the reality of one image than just using a decision of YES or NO. Results of experiments on several forgeries demonstrate the effectiveness of the technique.
Original languageEnglish
Pages (from-to)9-18
Number of pages10
JournalJournal of Visual Languages and Computing
Volume27
Early online date16 Feb 2015
DOIs
Publication statusPublished - Apr 2015

Fingerprint

Pixels
Forgery
Experiments

Keywords

  • tampered image
  • image forgery
  • feather operation
  • tampering detection

Cite this

Zheng, Jiangbin ; Zhu, Tingge ; Li, Zhe ; Xing, Weiwei ; Ren, Jinchang. / Exposing image forgery by detecting traces of feather operation. In: Journal of Visual Languages and Computing. 2015 ; Vol. 27. pp. 9-18.
@article{7d7eefa1dcfc44ac8e036d1f229aad1d,
title = "Exposing image forgery by detecting traces of feather operation",
abstract = "Powerful digital image editing tools make it very easy to produce a perfect image forgery. The feather operation is necessary when tampering an image by copy–paste operation because it can help the boundary of pasted object to blend smoothly and unobtrusively with its surroundings. We propose a blind technique capable of detecting traces of feather operation to expose image forgeries. We model the feather operation, and the pixels of feather region will present similarity in their gradient phase angle and feather radius. An effectual scheme is designed to estimate each feather region pixel׳s gradient phase angle and feather radius, and the pixel׳s similarity to its neighbor pixels is defined and used to distinguish the feathered pixels from un-feathered pixels. The degree of image credibility is defined, and it is more acceptable to evaluate the reality of one image than just using a decision of YES or NO. Results of experiments on several forgeries demonstrate the effectiveness of the technique.",
keywords = "tampered image, image forgery, feather operation, tampering detection",
author = "Jiangbin Zheng and Tingge Zhu and Zhe Li and Weiwei Xing and Jinchang Ren",
year = "2015",
month = "4",
doi = "10.1016/j.jvlc.2015.02.002",
language = "English",
volume = "27",
pages = "9--18",
journal = "Journal of Visual Languages and Computing",
issn = "1045-926X",

}

Exposing image forgery by detecting traces of feather operation. / Zheng, Jiangbin; Zhu, Tingge; Li, Zhe; Xing, Weiwei; Ren, Jinchang.

In: Journal of Visual Languages and Computing, Vol. 27, 04.2015, p. 9-18.

Research output: Contribution to journalSpecial issue

TY - JOUR

T1 - Exposing image forgery by detecting traces of feather operation

AU - Zheng, Jiangbin

AU - Zhu, Tingge

AU - Li, Zhe

AU - Xing, Weiwei

AU - Ren, Jinchang

PY - 2015/4

Y1 - 2015/4

N2 - Powerful digital image editing tools make it very easy to produce a perfect image forgery. The feather operation is necessary when tampering an image by copy–paste operation because it can help the boundary of pasted object to blend smoothly and unobtrusively with its surroundings. We propose a blind technique capable of detecting traces of feather operation to expose image forgeries. We model the feather operation, and the pixels of feather region will present similarity in their gradient phase angle and feather radius. An effectual scheme is designed to estimate each feather region pixel׳s gradient phase angle and feather radius, and the pixel׳s similarity to its neighbor pixels is defined and used to distinguish the feathered pixels from un-feathered pixels. The degree of image credibility is defined, and it is more acceptable to evaluate the reality of one image than just using a decision of YES or NO. Results of experiments on several forgeries demonstrate the effectiveness of the technique.

AB - Powerful digital image editing tools make it very easy to produce a perfect image forgery. The feather operation is necessary when tampering an image by copy–paste operation because it can help the boundary of pasted object to blend smoothly and unobtrusively with its surroundings. We propose a blind technique capable of detecting traces of feather operation to expose image forgeries. We model the feather operation, and the pixels of feather region will present similarity in their gradient phase angle and feather radius. An effectual scheme is designed to estimate each feather region pixel׳s gradient phase angle and feather radius, and the pixel׳s similarity to its neighbor pixels is defined and used to distinguish the feathered pixels from un-feathered pixels. The degree of image credibility is defined, and it is more acceptable to evaluate the reality of one image than just using a decision of YES or NO. Results of experiments on several forgeries demonstrate the effectiveness of the technique.

KW - tampered image

KW - image forgery

KW - feather operation

KW - tampering detection

UR - http://www.sciencedirect.com/science/article/pii/S1045926X15000075

U2 - 10.1016/j.jvlc.2015.02.002

DO - 10.1016/j.jvlc.2015.02.002

M3 - Special issue

VL - 27

SP - 9

EP - 18

JO - Journal of Visual Languages and Computing

JF - Journal of Visual Languages and Computing

SN - 1045-926X

ER -