Theme-Logo
  • Login
  • Home
  • Course
  • Publication
  • Theses
  • Reports
  • Published books
  • Workshops / Conferences
  • Supervised PhD
  • Supervised MSc
  • Supervised projects
  • Education
  • Language skills
  • Positions
  • Memberships and awards
  • Committees
  • Experience
  • Scientific activites
  • In links
  • Outgoinglinks
  • News
  • Gallery
publication name Copy-Move Forgery Detection Based on Automatic Threshold Estimation
Authors Aya Hegazi; Ahmed Taha; Mazen M Selim
year 2019
keywords Clustering Evaluation Measures, Copy-Move Detection, Image Forensics, Keypoint-Based Methods, Multiple- Copied Matching
journal International Journal of Sociotechnology and Knowledge Development (IJSKD).
volume 12
issue 1
pages 1-23
publisher Not Available
Local/International International
Paper Link Not Available
Full paper download
Supplementary materials Not Available
Abstract

Recently,usersandnewsfollowersacrosswebsitesfacemanyfabricatedimages.Moreover,itgoes farbeyondthattothepointofdefamingorimprisoningaperson.Hence,imageauthenticationhas becomeasignificantissue.Oneofthemostcommontamperingtechniquesiscopy-move.Keypoint- basedmethodsareconsideredasaneffectivemethodfordetectingcopy-moveforgeries.Insuch methods,thefeatureextractionprocessisfollowedbyapplyingaclusteringtechniquetogroupspatially closekeypoints.Mostclusteringtechniqueshighlydependontheexistenceofaspecificthreshold toterminatetheclustering.Determinationofthemostsuitablethresholdrequiresahugeamountof experiments.Inthisarticle,acopy-moveforgerydetectionmethodisproposed.Theproposedmethod isbasedonautomaticestimationoftheclusteringthreshold.Thecutoffthresholdofhierarchical clusteringisestimatedautomaticallybasedonclusteringevaluationmeasures.Experimentalresults testedonvariousdatasetsshowthattheproposedmethodoutperformsotherrelevantstate-of-the-art methods.

Benha University © 2023 Designed and developed by portal team - Benha University