Image Forgery Detection

Design and development of copy-move forgery detection technique.

1. Research Scholar’s Conclave presentation
on
Digital Image Forgery Detection using
Salient Keypoint Selection
Presented By:
NitishKumar
Ph.D. Scholar
Dept. of Electronics and Communication
Under the Guidance of:
Dr. Toshanlal Meenpal

2. Introduction
•Withtheadvancementofimageeditingtechniques,authenticityandreliabilityofdigitalimage
hasbecomeverychallenging.
•Realisticvisualeffectcanbeachievedinsuchawaythatforgedimagesarevisually
indistinguishablefromrealones.
•Image forgery aims to deliver deceptive information through the image graphic content.
•Imageforensicsverifytheauthenticity,ownership,andcopyrightofanimageanddetectchanges
totheoriginalimage.
Fig.1 Example of a forged image

3. Types of Image Forgery:
Image Forgery
Copy-move
Forgery
Image Splicing
Forgery
Image
Inpainting
Forgery
Fig.2 Types of image forgery

4. Clues of Image Forgery:
Table I. Forgery detection clues for different forgery techniques
Tampering
Clues
Copy-move Inpainting Splicing
Region Duplication Yes Yes No
Edge Anomaly
(Sharp Edges)
Yes No Yes
Edge Anomaly
(Blurred Edges)
Yes No Yes
Region Anomaly
(JPEG Double
Quantization)
No Yes Yes
Region Anomaly
(Lighting
inconsistency)
No No Yes
Region Anomaly
(Camera trace
inconsistency)
No No Yes

5. Proposed Copy-move Forgery Detection
Fig.3 Framework of proposed salient keypoint-based copy-move image forgery detection

6. Selection of Salient Keypoints
•Salient keypoints are selected by
ranking the keypoints based on 3
parameters.
1)Distinctiveness:Howdifferent
thekeypointisfromtherestof
thekeypointsintheimage.
2)Detectability:Howrobustlythe
keypointscanbedetectedunder
viewpoint/lightingchanges.
3)Repeatability:Itreferstothe
abilityofkeypointstoremain
invariant to various
transformations.
Fig.4 Visualization of reduction in number of keypoints

7. Results and Discussion
Fig.5 Comparison of number of keypoints for four
different images of size 512 x 512.
Fig.6 Detection of copy-move forgery on CoMoFoDdataset
where a) original image, b) forged image c) detection result

8. Cont..
Author Methods FPR PrecisionF1Score
Hashmi et. alDyWTand SIFT 10.00 88.89 85.00
Ojeniyiet al.DCT and SURF 6.36 93.86 95.45
Niyishakaet al.DoGand ORB - 90.09 86.24
Liu et. al CKN 7.27 93.16 96.03
Soniet al. SURF and 2NN 8.4 - -
Proposed SalientSIFT and KAZE 3.6 96.22 94.87
Table II. Comparison of proposed method with existing
techniques on the MICC-F220 dataset.
Author Methods FPR PrecisionF1Score
Malviyaet. alAutocolour correlogram 16 95.65 93.62
Soniet al. LBP-HP 7.40 - -
Mahmood et al.SWT - 95.76 96.05
Niyishakaet. alBloband BRISK 9 96.84 94.35
El Biachet al.Encoder-decoder - - 81.56
Proposed SalientSIFT and KAZE 6 97.90 95.73
Table III. Comparison of proposed method with existing
techniques on the CoMoFoDdataset.

9. Conclusion and Future Scope
•Inthisworkkeypoint-basedcopy–moveforgerydetectionhasbeenproposed
usingSIFTandKAZEfeatures.
•Salientkeypointsareselectedforreductioninnumberofkeypoints.
•ProposeddetectionapproachhasbeenevaluatedonCoMoFoDandMICC-F220
datasetsandgivespromisingresultsundergeometrictransformationsandcommon
post-processingoperations.
•Asafuturework,detectionofotherimageforgeryapproachcanbeproposed.
•Robustdetectionalgorithmcanalsobeproposedwhichcandetectanykindof
imageforgery.

10. References
[1]ZhengL,ZhangY,ThingVL.Asurveyonimagetamperinganditsdetectioninreal-worldphotos.JVisual
CommunImageRepresent.2019;58:380–399.doi:10.1016/j.jvcir.2018.12.022.
[2]HashmiMF,AnandV,KeskarAG.Copy-moveimageforgerydetectionusinganefficientandrobustmethod
combiningun-decimatedwavelettransformandscaleinvariantfeaturetransform.AasriProcedia.2014;9:84–
91.
[3]NiyishakaP,BhagvatiC.Digitalimageforensicstechniqueforcopy-moveforgerydetectionusingDOGand
ORB.Internationalconferenceoncomputervisionandgraphics;2018.p.472–483.
[4]NiyishakaP,BhagvatiC.Copy-moveforgerydetectionusingimageblobsandbriskfeature.Multimedia
ToolsAppl.2020;79(35):26045–26059.doi:10.1007/s11042-020-09225-6.
[5]X.Niu,H.Han,S.Shan,andX.Chen,“Synrhythm:Learningadeepheartrateestimatorfromgeneralto
specific,”in201824thInternationalConferenceonPatternRecognition(ICPR),pp.3580–3585,IEEE,(2018).
[6]MukherjeeP,LallB.SaliencyandKAZEfeaturesassistedobjectsegmentation.ImageVisComput.
2017;61:82–97.Availablefrom:https://www.sciencedirect.com/science/article/pii/S0262885617300537.
[7]LoweDG.Objectrecognitionfromlocalscale-invariantfeatures.ProceedingsoftheSeventhIEEE
InternationalConferenceonComputerVision;1999.Vol.2,p.1150–1157.
[8]AlcantarillaPF,BartoliA,DavisonAJ.KAZEfeatures.In:FitzgibbonA,LazebnikS,PeronaP,SatoY,
SchmidC,editors.Computervisioneccv2012.Berlin(Heidelberg):Springer;2012.p.214–227.