A Bayesian-MRF Approach for PRNU-Based Image Forgery Detection

Chierchia, Giovanni; Poggi, Gianfranco; Sansone, Carlo; Verdoliva, Luisa

doi:10.1109/tifs.2014.2302078

Cited by 169 publications

(95 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One is the accuracy of the fingerprints extracted from images. Various forms of device fingerprints such as sensor pattern noise (SPN) [1][2][3][4][5][6][7][8][9][10][11][12], camera response function [13], re-sampling artifacts [14], color filter array (CFA) interpolation artifacts [15,16], JPEG compression [17], and lens aberration [12,18] have been proposed in recent years. Other device and image attributes such as binary similarity measures, image quality measures, and higher order wavelet statistics have also been adopted for identifying source imaging devices [19][20][21][22].…”

Section: The Challenges Of Source-oriented Image Clustering and Relatmentioning

confidence: 99%

“…Other device and image attributes such as binary similarity measures, image quality measures, and higher order wavelet statistics have also been adopted for identifying source imaging devices [19][20][21][22]. While many methods [13][14][15][16] make specific assumptions in their applications, SPN-based methods [1][2][3][4][5][6][7][8][9][10][11][12] do not require such assumptions to be satisfied and thus have drawn much more attention. Another merit of SPN is that it is unique to each device, which means it is capable of differentiating individual devices of the same model [1,3,5,11].…”

Section: The Challenges Of Source-oriented Image Clustering and Relatmentioning

confidence: 99%

“…Our previous experience of using Markov random field (MRF) approach to image segmentation [53,54] and many others' successful applications of MRF [9,[55][56][57] suggest that the local characteristics of MRFs (also known as Markovianity) allow global optimization problems to be solved iteratively by taking local information into account. Suppose there are K classes of images in the subset, with the value of K unknown, and denote D = {d k |k = 1, 2, .…”

Section: Clusteringmentioning

confidence: 99%

See 2 more Smart Citations

A fast source-oriented image clustering method for digital forensics

Lin

2017

J Image Video Proc.

View full text Add to dashboard Cite

We present in this paper an algorithm that is capable of clustering images taken by an unknown number of unknown digital cameras into groups, such that each contains only images taken by the same source camera. It first extracts a sensor pattern noise (SPN) from each image, which serves as the fingerprint of the camera that has taken the image. The image clustering is performed based on the pairwise correlations between camera fingerprints extracted from images. During this process, each SPN is treated as a random variable and a Markov random field (MRF) approach is employed to iteratively assign a class label to each SPN (i.e., random variable). The clustering process requires no a priori knowledge about the dataset from the user. A concise yet effective cost function is formulated to allow different "neighbors" different voting power in determining the class label of the image in question depending on their similarities. Comparative experiments were carried out on the Dresden image database to demonstrate the advantages of the proposed clustering algorithm.

show abstract

Section: The Challenges Of Source-oriented Image Clustering and Relatmentioning

confidence: 99%

Section: The Challenges Of Source-oriented Image Clustering and Relatmentioning

confidence: 99%

Section: Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

A fast source-oriented image clustering method for digital forensics

Lin

2017

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…Markov random fields are used to model the spatial dependences of the source that're strong [4]. The problem formulation takes the lead from the prior knowledge on the image, as this process is based on Bayesian approach.…”

Section: E Bayesian Markov Random Field Approach-mentioning

confidence: 99%

Study of various detection techniques of tampered regions in digital image forensics

2016

IJLTET

View full text Add to dashboard Cite

“…Techniques based on the photo-response nonuniformity (PRNU) that detect the absence of the camera PRNU, a sort of camera fingerprint, are explored in [16]. This algorithm detects image forgeries using sensor pattern noise.…”

Section: Image Retouchingmentioning

confidence: 99%