Copy-Move Forgery Detection Using SWT-DCT and Four Square Mean Features

Fauhan Handay Pugar, Sultan Muzahidin, Aniati Murni Arymurthy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Image forgery detection is challenging to solve, especially in blind image forgery detection. Copy-move forgery is a common and popular method in image forgery. Copy-move forgery become more challenging to detect with addition of post-processing operation in the image. In this paper, the proposed methodology is copy-move detection with Stationary Wavelet Transform (SWT), Discrete Cosine Transform (DCT), and Four-Square Mean Features. SWT is used because it enables to handle various kind of post-processing operation. Likewise, DCT has many advantages such as the lower dimension and robust to various attacks. The proposed methodology is evaluated using CoMoFoD dataset and the performance are measured using precision, recall, and F1-scores. The result reveal that the methodology is successful in detecting duplicated region and robust against brightness change, contrast adjustment, image blurring, and color reduction.

Original languageEnglish
Title of host publicationProceeding of 2019 International Conference on Electrical Engineering and Informatics, ICEEI 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages63-68
Number of pages6
ISBN (Electronic)9781728124186
DOIs
Publication statusPublished - Jul 2019
Event7th International Conference on Electrical Engineering and Informatics, ICEEI 2019 - Bandung, Indonesia
Duration: 9 Jul 201910 Jul 2019

Publication series

NameProceedings of the International Conference on Electrical Engineering and Informatics
Volume2019-July
ISSN (Print)2155-6830

Conference

Conference7th International Conference on Electrical Engineering and Informatics, ICEEI 2019
Country/TerritoryIndonesia
CityBandung
Period9/07/1910/07/19

Keywords

  • copy-move forgery
  • discrete cosine transform
  • four square mean features
  • image forgery
  • stationary wavelet transform

Fingerprint

Dive into the research topics of 'Copy-Move Forgery Detection Using SWT-DCT and Four Square Mean Features'. Together they form a unique fingerprint.

Cite this