Staff Members - Benha University
Copy-Move Forgery Detection Based on Automatic Threshold Estimation
International Journal of Sociotechnology and Knowledge Development (IJSKD). • 2019
Publication Information
Authors
Aya Hegazi; Ahmed Taha; Mazen M Selim
Keywords
Clustering Evaluation Measures, Copy-Move Detection, Image Forensics, Keypoint-Based Methods, Multiple- Copied Matching
Journal
International Journal of Sociotechnology and Knowledge Development (IJSKD).
Publisher
Not Available
Volume
12
Issue
1
Pages
1-23
publication.type
International
Paper Link
Not Available
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.