A bibliography of pixel-based blind image forgery detection techniques

Qureshi, Muhammad Ali; Deriche, Mohamed

doi:10.1016/j.image.2015.08.008

Cited by 144 publications

(55 citation statements)

References 171 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The diverse arrangements of separation (indicated by d) and edges (meant by θ) between the two pixels can impact the method for computing the quantity of the pixel couples in GLCM. In TF-GLCM, the separation is set at 1 and the edges are 0°, 45°, 90°, and 135° [11]. What's more, these two parameters (d and θ) would bring about four types of grouping.…”

Section: ) Gray Level Co-occurrence Matrices (Glcm)mentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach for Efficient Forgery Image Detection Using Hybrid Feature Extraction and Classification

Shanthi¹,

Raj²

2018

IJET

View full text Add to dashboard Cite

Image forgery detection is developing as one of the major research topic among researchers in the area of image forensics. These image forgery detection is addressed by two different types: (i) Active, (ii) Passive. Further consist of some different methods, s uch as Copy-Move, Image Splicing, and Retouching. Development of the image forgery is very necessary to detect as the image is true or it is forgery. In this paper, an efficient forgery detection and classification technique is proposed by three different stages. At first stage, preprocessing is carried out using bilateral filtering to remove noise. At second stage, extract unique features from forged image by using efficient feature extraction technique namely Gray Level Co-occurance Matrices (GLCM). Here, the GLCM improves the feature extraction accuracy. Finally, forged image is detected by classifying the type of image forgery using Multi Class-Support Vector Machine (SVM). Also, the performance of the proposed method is analyzed using the following metrics: accuracy, sensitivity and specificity.

show abstract

Section: ) Gray Level Co-occurrence Matrices (Glcm)mentioning

confidence: 99%

“…Also the MC-SVM is considered into four important methods such as: Directed Acyclic Graph (DAG), Binary Tree (BT), One Against-One (OAO), One-Against-All (OAA) classifiers. Generally SVM class label requires two values such as ± 1, it can be called as bilinear classifier [11]. MC-SVM classifier is constructed by f 1, f 2, .…”

Section: Classifiermentioning

confidence: 99%

A Novel Approach for Efficient Forgery Image Detection Using Hybrid Feature Extraction and Classification

Shanthi¹,

Raj²

2018

IJET

View full text Add to dashboard Cite

show abstract

“…Broadly, the classification of digital image tampering detection schemes is done in two categories, namely active techniques and passive techniques [3]. In active schemes, prior information about an image is absolutely necessary for authentication, which limits their application.…”

Section: Introductionmentioning

confidence: 99%

Digital image copy-move forgery detection based on discrete fractional wavelet transform

2018

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:With the advancement of sophisticated cameras and image editing software tools, digital image tampering techniques are frequently used without leaving visual cues behind. Digital image copy-move forgery is a kind of image manipulation that involves copying and pasting of a certain section (or sections) within the same digital image. Generally, this is done with false intentions of hiding important information or providing false information in an image. In view of this, the focus of the present paper is to propose a discrete fractional wavelet transform-based scheme for identification of duplicated regions in the image. The test image is split into overlapping image blocks with fixed dimensions. Then, on each image block, discrete fractional wavelet transform is employed for the extraction of their features. All the feature vectors are systematized in lexicographical manner followed by the block matching and block filtering steps to obtain the replicated blocks, if any. The proposed method can detect single and multiple duplicated regions successfully. The results are compared to existing techniques based on precision and recall parameters. Simulation results show that the proposed forgery detection scheme can detect tampering areas even in the presence of distortions due to Gaussian blurring and JPEG compression.

show abstract

“…There exist various statistics such as CFA interpolation, resampling artifacts, motion blur, lightning intensity, reflections, edges, and JPEG fingerprint, which are consistent in the untampered images [1,2]. Recently in [3], the authors provided a comprehensive survey of different forgery detection techniques such as copymove forgery, splicing, resampling, and image retouching. Mostly, they covered pixel-based techniques, as these techniques do not require any a priori information about the type of tampering.…”

Section: Introductionmentioning

confidence: 99%

Automated approach for splicing detection using first digit probability distribution features

Mire

Dhok

Mistry

et al. 2018

J Image Video Proc.

View full text Add to dashboard Cite

Digital image tampering operations destroy inbuilt fingerprints and create own new fingerprint in the tampered region. Considering the Internet speed and storage space, most of the images are circulated in the JPEG format. In a single compressed JPEG image, the first digits of DCT coefficients follow a logarithmic distribution. This distribution is not followed by DCT coefficients of DCT grid aligned double compressed images. In a tampered image, the major portion of the original JPEG image is aligned double JPEG compressed. Hence, untampered region does not follow this logarithmic distribution. Due to the nonalignment of DCT compression grids, tampered region still follows this logarithmic distribution. Many tampering localization techniques have investigated this fingerprint, but the majority of them uses SVM classifier, specifically trained for the respective primary and secondary compression qualities of the test images. The efficiency of these classifiers is dependent on the knowledge of tampered image compression history. Hence, these approaches are not fully automated. In this paper, we have investigated a method, which does not require prior compression quality knowledge. Our experimental analysis shows that the addition of Gaussian noise can make the probability distribution of an aligned double compressed image similar to a nonaligned double compressed image. We divided the test image and its Gaussian version into sub-images and clustered them using K-means clustering algorithm. The application of K-means clustering algorithm does not require compression quality knowledge. This makes our approach more practical as compared to the other first digit probability distribution-based algorithms. The proposed algorithm gives compatible performance with the other approaches, based on different JPEG fingerprints.

show abstract

A bibliography of pixel-based blind image forgery detection techniques

Cited by 144 publications

References 171 publications

A Novel Approach for Efficient Forgery Image Detection Using Hybrid Feature Extraction and Classification

A Novel Approach for Efficient Forgery Image Detection Using Hybrid Feature Extraction and Classification

Digital image copy-move forgery detection based on discrete fractional wavelet transform

Automated approach for splicing detection using first digit probability distribution features

Contact Info

Product

Resources

About