Cloning Localization Based on Feature Extraction and K-means Clustering

Alfraih, Areej S.; Briffa, Johann A.; Wesemeyer, Stephan

doi:10.1007/978-3-319-19321-2_31

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…27 We found that simple thresholds were not effective under a wide range of tampering scenarios and could only be tuned for specific conditions. This improves on simpler techniques, such as the use of simple thresholds, which we adopted in our earlier work.…”

Section: Classifying Clusters Of Matchesmentioning

confidence: 79%

Cloning localization approach using k -means clustering and support vector machine

Alfraih

Briffa

Wesemeyer

2015

J. Electron. Imaging

Self Cite

View full text Add to dashboard Cite

Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspxAbstract. Passive forensics is increasing in significance due to the availability of various software tools that can be used to alter original content without visible traces and the increasing public awareness of such tampering. Many passive image tamper detection techniques have been proposed in the literature, some of which use feature extraction methods for tamper detection and localization. This work proposes a flexible methodology for detecting cloning in images based on the use of feature detectors. We determine whether a particular match is the result of a cloning event by clustering the matches using k-means clustering and using a support vector machine to classify the clusters. This descriptor-agnostic approach allows us to combine the results of multiple feature descriptors, increasing the potential number of keypoints in the cloned region. Results using maximally stable extremal regions' features, speeded up robust features, and scale-invariant feature transform show a very significant improvement over the state of the art, particularly when different descriptors are combined. A statistical filtering step is also proposed, increasing the homogeneity of the clusters and thereby improving the results. Finally, our methodology uses an adaptive technique for independently selecting the optimal k value for each image, allowing our method to work well when there are multiple cloned regions. We also show that our methodology works well when the training and testing datasets are mismatched. © 2015 SPIE and IS&T [Alfraih, Briffa, and Wesemeyer: Cloning localization approach using k -means clustering. . . Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Alfraih, Briffa, and Wesemeyer: Cloning localization approach using k -means clustering. . . Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Alfraih, Briffa, and Wesemeyer: Cloning localization approach using k -means clustering. . . Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Alfraih, Briffa, and Wesemeyer: Cloning localization approach using k -means clustering. . . Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Alfraih, Briffa, and Wesemeyer: Cloning localization approach using k -means clustering. . . Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Alfraih, Briffa, and Wesemeyer: Cloning localization approach using k -means clustering. . . Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/25/2015 Terms of Use: http://spiedigital...

show abstract

Section: Classifying Clusters Of Matchesmentioning

confidence: 79%

Cloning localization approach using k -means clustering and support vector machine

Alfraih

Briffa

Wesemeyer

2015

J. Electron. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…It furnishes that performance of the proposed method is well improved in terms of FPR when compared with all the methods and it is improved some extend in terms of TPR compared to the Areej et. al [24]. [14] 11.61 93.42 In addition, the robustness of the proposed system is tested for JPEG compression and noise.…”

Section: Resultsmentioning

confidence: 99%

“…The method in [23], extracted the contrast context histogram features to detect the forgery. In [24], authors detected the forgery using the maximum stable extremal regions (MSER).…”

Section: Related Workmentioning

confidence: 99%

Visual Feature Based Image Forgery Detection

Vaishnavi¹,

Mahalakshmi²,

Alapati³

2018

IJET

View full text Add to dashboard Cite

In present days, the images are building up in digital form and which may hold essential information. Such images can be voluntarily forged or manipulated using the image processing tools to abuse it. It is very complicated to notice the forgery by naked eye s. In particular, the copy move forgery is enormously demanding one to expose. Hence, this paper put forwards a method to determine the copy move forgery by extracting the visual feature called speed up robust features (SURF). In the direction to quantitatively analyze the performance, the metrics namely false positive rate and true positive rate are estimated and also comparative study is carried out by previous existing methods.

show abstract