Spotting the difference: Context retrieval and analysis for improved forgery detection and localization

Joel Brogan; Paolo Bestagini; Aparna Bharati; Allan Pinto; Daniel Moreira; Kevin Bowyer; Patrick Flynn; Anderson Rocha; Walter Scheirer

doi:10.1109/ICIP.2017.8297049

Spotting the difference: Context retrieval and analysis for improved forgery detection and localization

Joel Brogan, Paolo Bestagini, Aparna Bharati, Allan Pinto, Daniel Moreira, Kevin Bowyer, Patrick Flynn, Anderson Rocha, Walter Scheirer

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

As image tampering becomes ever more sophisticated and commonplace, the need for image forensics algorithms that can accurately and quickly detect forgeries grows. In this paper, we revisit the ideas of image querying and retrieval to provide clues to better localize forgeries. We propose a method to perform large-scale image forensics on the order of one million images using the help of an image search algorithm and database to gather contextual clues as to where tampering may have taken place. In this vein, we introduce five new strongly invariant image comparison methods and test their effectiveness under heavy noise, rotation, and color space changes. Lastly, we show the effectiveness of these methods compared to passive image forensics using Nimble [1], a new, state-of-the-art dataset from the National Institute of Standards and Technology (NIST).

Original language	English
Title of host publication	2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
Publisher	IEEE Computer Society
Pages	4078-4082
Number of pages	5
ISBN (Electronic)	9781509021758
DOIs	https://doi.org/10.1109/ICIP.2017.8297049
State	Published - Jul 2 2017
Externally published	Yes
Event	24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China Duration: Sep 17 2017 → Sep 20 2017

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2017-September
ISSN (Print)	1522-4880

Conference

Conference	24th IEEE International Conference on Image Processing, ICIP 2017
Country/Territory	China
City	Beijing
Period	09/17/17 → 09/20/17

Funding

This material is based on research sponsored by DARPA and Air Force Research Laboratory (AFRL) under agreement number FA8750-16-2-0173. Hardware support was generously provided by the NVIDIA Corporation. We also thank the financial support of FAPESP (Grant #2015/19222-9), CAPES (DeepEyes Grant) and CNPq (Grant #304472/2015-8).

Funders	Funder number
Defense Advanced Research Projects Agency
Air Force Research Laboratory	FA8750-16-2-0173
Fundação de Amparo à Pesquisa do Estado de São Paulo	2015/19222-9
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
Conselho Nacional de Desenvolvimento Científico e Tecnológico	304472/2015-8

Keywords

Context-aware digital forensics
Forgery detection
Image forensics
Splicing detection
Tampering heat maps

Access to Document

10.1109/ICIP.2017.8297049

Cite this

Brogan, J., Bestagini, P., Bharati, A., Pinto, A., Moreira, D., Bowyer, K., Flynn, P., Rocha, A., & Scheirer, W. (2017). Spotting the difference: Context retrieval and analysis for improved forgery detection and localization. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (pp. 4078-4082). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8297049

@inproceedings{4bfa00e2007a4ed4bfb3082db73e6063,

title = "Spotting the difference: Context retrieval and analysis for improved forgery detection and localization",

abstract = "As image tampering becomes ever more sophisticated and commonplace, the need for image forensics algorithms that can accurately and quickly detect forgeries grows. In this paper, we revisit the ideas of image querying and retrieval to provide clues to better localize forgeries. We propose a method to perform large-scale image forensics on the order of one million images using the help of an image search algorithm and database to gather contextual clues as to where tampering may have taken place. In this vein, we introduce five new strongly invariant image comparison methods and test their effectiveness under heavy noise, rotation, and color space changes. Lastly, we show the effectiveness of these methods compared to passive image forensics using Nimble [1], a new, state-of-the-art dataset from the National Institute of Standards and Technology (NIST).",

keywords = "Context-aware digital forensics, Forgery detection, Image forensics, Splicing detection, Tampering heat maps",

author = "Joel Brogan and Paolo Bestagini and Aparna Bharati and Allan Pinto and Daniel Moreira and Kevin Bowyer and Patrick Flynn and Anderson Rocha and Walter Scheirer",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 24th IEEE International Conference on Image Processing, ICIP 2017 ; Conference date: 17-09-2017 Through 20-09-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICIP.2017.8297049",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "4078--4082",

booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",

}

Brogan, J, Bestagini, P, Bharati, A, Pinto, A, Moreira, D, Bowyer, K, Flynn, P, Rocha, A & Scheirer, W 2017, Spotting the difference: Context retrieval and analysis for improved forgery detection and localization. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2017-September, IEEE Computer Society, pp. 4078-4082, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 09/17/17. https://doi.org/10.1109/ICIP.2017.8297049

Spotting the difference: Context retrieval and analysis for improved forgery detection and localization. / Brogan, Joel; Bestagini, Paolo; Bharati, Aparna et al.
2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2017. p. 4078-4082 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Spotting the difference

T2 - 24th IEEE International Conference on Image Processing, ICIP 2017

AU - Brogan, Joel

AU - Bestagini, Paolo

AU - Bharati, Aparna

AU - Pinto, Allan

AU - Moreira, Daniel

AU - Bowyer, Kevin

AU - Flynn, Patrick

AU - Rocha, Anderson

AU - Scheirer, Walter

PY - 2017/7/2

Y1 - 2017/7/2

N2 - As image tampering becomes ever more sophisticated and commonplace, the need for image forensics algorithms that can accurately and quickly detect forgeries grows. In this paper, we revisit the ideas of image querying and retrieval to provide clues to better localize forgeries. We propose a method to perform large-scale image forensics on the order of one million images using the help of an image search algorithm and database to gather contextual clues as to where tampering may have taken place. In this vein, we introduce five new strongly invariant image comparison methods and test their effectiveness under heavy noise, rotation, and color space changes. Lastly, we show the effectiveness of these methods compared to passive image forensics using Nimble [1], a new, state-of-the-art dataset from the National Institute of Standards and Technology (NIST).

AB - As image tampering becomes ever more sophisticated and commonplace, the need for image forensics algorithms that can accurately and quickly detect forgeries grows. In this paper, we revisit the ideas of image querying and retrieval to provide clues to better localize forgeries. We propose a method to perform large-scale image forensics on the order of one million images using the help of an image search algorithm and database to gather contextual clues as to where tampering may have taken place. In this vein, we introduce five new strongly invariant image comparison methods and test their effectiveness under heavy noise, rotation, and color space changes. Lastly, we show the effectiveness of these methods compared to passive image forensics using Nimble [1], a new, state-of-the-art dataset from the National Institute of Standards and Technology (NIST).

KW - Context-aware digital forensics

KW - Forgery detection

KW - Image forensics

KW - Splicing detection

KW - Tampering heat maps

UR - http://www.scopus.com/inward/record.url?scp=85045292839&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8297049

DO - 10.1109/ICIP.2017.8297049

M3 - Conference contribution

AN - SCOPUS:85045292839

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 4078

EP - 4082

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

Y2 - 17 September 2017 through 20 September 2017

ER -

Brogan J, Bestagini P, Bharati A, Pinto A, Moreira D, Bowyer K et al. Spotting the difference: Context retrieval and analysis for improved forgery detection and localization. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society. 2017. p. 4078-4082. (Proceedings - International Conference on Image Processing, ICIP). doi: 10.1109/ICIP.2017.8297049

Spotting the difference: Context retrieval and analysis for improved forgery detection and localization

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this