| 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.