Doctored JPEG image detection

Weihai Li*, Nenghai Yu, Yuan Yuan

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Nowadays, digital images can be easily modified by using software. In this paper, a new blind approach is proposed to detect copy-paste trail in a doctored JPEG image, i.e., to check whether a copied area came from the same image or not. When a copy-paste procedure is done on an image, especially adding or hiding an object, the block artifact grid contained in the copy-pasted slice is moved together. Since a slice must be placed properly in the target image to avoid obvious vision flaw, the grid in the slice mismatches to the original grid in the target image normally. Our approach utilizes the mismatch information of block artifact grid as a clue of copy-paste forgery. Experiment results demonstrate the efficiency of the proposed approach.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings
Pages253-256
Number of pages4
DOIs
Publication statusPublished - 23 Oct 2008
Event2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Hannover, United Kingdom
Duration: 23 Jun 200826 Jun 2008

Conference

Conference2008 IEEE International Conference on Multimedia and Expo, ICME 2008
CountryUnited Kingdom
CityHannover
Period23/06/0826/06/08

Fingerprint

Defects
Experiments

Keywords

  • Block artifact
  • Copy-paste forgery
  • DCT grid
  • JPEG standard
  • Passive image forensics

Cite this

Li, W., Yu, N., & Yuan, Y. (2008). Doctored JPEG image detection. In 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings (pp. 253-256). [4607419] https://doi.org/10.1109/ICME.2008.4607419
Li, Weihai ; Yu, Nenghai ; Yuan, Yuan. / Doctored JPEG image detection. 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings. 2008. pp. 253-256
@inproceedings{acfaafb142cb474c9f9f70414d75fa83,
title = "Doctored JPEG image detection",
abstract = "Nowadays, digital images can be easily modified by using software. In this paper, a new blind approach is proposed to detect copy-paste trail in a doctored JPEG image, i.e., to check whether a copied area came from the same image or not. When a copy-paste procedure is done on an image, especially adding or hiding an object, the block artifact grid contained in the copy-pasted slice is moved together. Since a slice must be placed properly in the target image to avoid obvious vision flaw, the grid in the slice mismatches to the original grid in the target image normally. Our approach utilizes the mismatch information of block artifact grid as a clue of copy-paste forgery. Experiment results demonstrate the efficiency of the proposed approach.",
keywords = "Block artifact, Copy-paste forgery, DCT grid, JPEG standard, Passive image forensics",
author = "Weihai Li and Nenghai Yu and Yuan Yuan",
year = "2008",
month = "10",
day = "23",
doi = "10.1109/ICME.2008.4607419",
language = "English",
isbn = "9781424425716",
pages = "253--256",
booktitle = "2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings",

}

Li, W, Yu, N & Yuan, Y 2008, Doctored JPEG image detection. in 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings., 4607419, pp. 253-256, 2008 IEEE International Conference on Multimedia and Expo, ICME 2008, Hannover, United Kingdom, 23/06/08. https://doi.org/10.1109/ICME.2008.4607419

Doctored JPEG image detection. / Li, Weihai; Yu, Nenghai; Yuan, Yuan.

2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings. 2008. p. 253-256 4607419.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Doctored JPEG image detection

AU - Li, Weihai

AU - Yu, Nenghai

AU - Yuan, Yuan

PY - 2008/10/23

Y1 - 2008/10/23

N2 - Nowadays, digital images can be easily modified by using software. In this paper, a new blind approach is proposed to detect copy-paste trail in a doctored JPEG image, i.e., to check whether a copied area came from the same image or not. When a copy-paste procedure is done on an image, especially adding or hiding an object, the block artifact grid contained in the copy-pasted slice is moved together. Since a slice must be placed properly in the target image to avoid obvious vision flaw, the grid in the slice mismatches to the original grid in the target image normally. Our approach utilizes the mismatch information of block artifact grid as a clue of copy-paste forgery. Experiment results demonstrate the efficiency of the proposed approach.

AB - Nowadays, digital images can be easily modified by using software. In this paper, a new blind approach is proposed to detect copy-paste trail in a doctored JPEG image, i.e., to check whether a copied area came from the same image or not. When a copy-paste procedure is done on an image, especially adding or hiding an object, the block artifact grid contained in the copy-pasted slice is moved together. Since a slice must be placed properly in the target image to avoid obvious vision flaw, the grid in the slice mismatches to the original grid in the target image normally. Our approach utilizes the mismatch information of block artifact grid as a clue of copy-paste forgery. Experiment results demonstrate the efficiency of the proposed approach.

KW - Block artifact

KW - Copy-paste forgery

KW - DCT grid

KW - JPEG standard

KW - Passive image forensics

UR - http://www.scopus.com/inward/record.url?scp=54049126209&partnerID=8YFLogxK

U2 - 10.1109/ICME.2008.4607419

DO - 10.1109/ICME.2008.4607419

M3 - Conference contribution

AN - SCOPUS:54049126209

SN - 9781424425716

SP - 253

EP - 256

BT - 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings

ER -

Li W, Yu N, Yuan Y. Doctored JPEG image detection. In 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings. 2008. p. 253-256. 4607419 https://doi.org/10.1109/ICME.2008.4607419