JPEG image classification in digital forensic via DCT coefficient analysis

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

From the digital forensics point of view, image forgery is considered as evidence that could provide a major breakthrough in the investigation process. Additionally, the development of storage device technologies has increased storage space significantly. Thus a digital investigator can be overwhelmed by the amount of data on storage devices that needs to be analysed. In this paper, we propose a model for classifying bulk JPEG images produced by the data carving process or other means into three different classes to solve the problem of identifying forgery quickly and effectively. The first class is JPEG images that contain errors or corrupted data, the second class is JPEG images that contain forged regions, and the third is JPEG images that have no signs of corruption or forgery. To test the proposed model, some experiments were conducted on our own dataset in addition to CASIA V2 image forgery dataset. The experiments covered different types of forgery technique. The results yielded around 88% accuracy rate in the classification process using five different machine learning methods on CASIA V2 dataset. It can be concluded that the proposed model can help investigators to automatically classify JPEG images, which reduce the time needed in the overall digital investigation process.

Original languageEnglish
Pages (from-to)1-31
Number of pages31
JournalMultimedia Tools and Applications
DOIs
Publication statusAccepted/In press - 4 Jul 2017

Fingerprint

Image classification
Learning systems
Experiments
Digital forensics

Keywords

  • Data carving
  • DCT coefficient analysis
  • Digital investigation
  • JPEG image classification
  • JPEG image forgery

ASJC Scopus subject areas

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

JPEG image classification in digital forensic via DCT coefficient analysis. / Alherbawi, Nadeem; Shukur, Zarina; Sulaiman, Rossilawati.

In: Multimedia Tools and Applications, 04.07.2017, p. 1-31.

Research output: Contribution to journalArticle

@article{e4cb32a5b883420dbc06b301958d539c,
title = "JPEG image classification in digital forensic via DCT coefficient analysis",
abstract = "From the digital forensics point of view, image forgery is considered as evidence that could provide a major breakthrough in the investigation process. Additionally, the development of storage device technologies has increased storage space significantly. Thus a digital investigator can be overwhelmed by the amount of data on storage devices that needs to be analysed. In this paper, we propose a model for classifying bulk JPEG images produced by the data carving process or other means into three different classes to solve the problem of identifying forgery quickly and effectively. The first class is JPEG images that contain errors or corrupted data, the second class is JPEG images that contain forged regions, and the third is JPEG images that have no signs of corruption or forgery. To test the proposed model, some experiments were conducted on our own dataset in addition to CASIA V2 image forgery dataset. The experiments covered different types of forgery technique. The results yielded around 88{\%} accuracy rate in the classification process using five different machine learning methods on CASIA V2 dataset. It can be concluded that the proposed model can help investigators to automatically classify JPEG images, which reduce the time needed in the overall digital investigation process.",
keywords = "Data carving, DCT coefficient analysis, Digital investigation, JPEG image classification, JPEG image forgery",
author = "Nadeem Alherbawi and Zarina Shukur and Rossilawati Sulaiman",
year = "2017",
month = "7",
day = "4",
doi = "10.1007/s11042-017-4915-3",
language = "English",
pages = "1--31",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - JPEG image classification in digital forensic via DCT coefficient analysis

AU - Alherbawi, Nadeem

AU - Shukur, Zarina

AU - Sulaiman, Rossilawati

PY - 2017/7/4

Y1 - 2017/7/4

N2 - From the digital forensics point of view, image forgery is considered as evidence that could provide a major breakthrough in the investigation process. Additionally, the development of storage device technologies has increased storage space significantly. Thus a digital investigator can be overwhelmed by the amount of data on storage devices that needs to be analysed. In this paper, we propose a model for classifying bulk JPEG images produced by the data carving process or other means into three different classes to solve the problem of identifying forgery quickly and effectively. The first class is JPEG images that contain errors or corrupted data, the second class is JPEG images that contain forged regions, and the third is JPEG images that have no signs of corruption or forgery. To test the proposed model, some experiments were conducted on our own dataset in addition to CASIA V2 image forgery dataset. The experiments covered different types of forgery technique. The results yielded around 88% accuracy rate in the classification process using five different machine learning methods on CASIA V2 dataset. It can be concluded that the proposed model can help investigators to automatically classify JPEG images, which reduce the time needed in the overall digital investigation process.

AB - From the digital forensics point of view, image forgery is considered as evidence that could provide a major breakthrough in the investigation process. Additionally, the development of storage device technologies has increased storage space significantly. Thus a digital investigator can be overwhelmed by the amount of data on storage devices that needs to be analysed. In this paper, we propose a model for classifying bulk JPEG images produced by the data carving process or other means into three different classes to solve the problem of identifying forgery quickly and effectively. The first class is JPEG images that contain errors or corrupted data, the second class is JPEG images that contain forged regions, and the third is JPEG images that have no signs of corruption or forgery. To test the proposed model, some experiments were conducted on our own dataset in addition to CASIA V2 image forgery dataset. The experiments covered different types of forgery technique. The results yielded around 88% accuracy rate in the classification process using five different machine learning methods on CASIA V2 dataset. It can be concluded that the proposed model can help investigators to automatically classify JPEG images, which reduce the time needed in the overall digital investigation process.

KW - Data carving

KW - DCT coefficient analysis

KW - Digital investigation

KW - JPEG image classification

KW - JPEG image forgery

UR - http://www.scopus.com/inward/record.url?scp=85021785305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021785305&partnerID=8YFLogxK

U2 - 10.1007/s11042-017-4915-3

DO - 10.1007/s11042-017-4915-3

M3 - Article

AN - SCOPUS:85021785305

SP - 1

EP - 31

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

ER -