A novel dual-threshold SIFT-based copy-move forgery detection

Haoqing Luan, Ngai Fong Law

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Given the large number of digital images in Internet and social networks, verification of image integrity is crucial. Copy-move forgery is one of the most common types of forgery. Through this kind of forgery, undesired objects are hidden or desired objects are duplicated so that the meaning in the images is altered. This paper proposed a robust matching method for SIFT-based copy-move forgery detection. The use of dual thresholds can reliably detect multiple copied and moved regions in an image. Experimental results have shown that the proposed method is robust towards occlusions and different degrees of geometric manipulations such as rotation and scaling.
Original languageEnglish
Title of host publication2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016
PublisherIEEE
ISBN (Electronic)9789881476821
DOIs
Publication statusPublished - 17 Jan 2017
Event2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016 - Jeju, Korea, Republic of
Duration: 13 Dec 201616 Dec 2016

Conference

Conference2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016
Country/TerritoryKorea, Republic of
CityJeju
Period13/12/1616/12/16

Keywords

  • Copy moveforgery detection
  • Dual-Threshold matching method
  • SIFT

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems
  • Signal Processing

Cite this