Image splicing detection based on Markov features in discrete octonion cosine transform domain

Abstract

To improve the poor robustness and low accuracy of the existing algorithms of image splicing detection, a novel passive image forgery detection method is proposed in this study, which is based on DOCT (discrete octonion cosine transform) and Markov. By introducing the octonion and DOCT, the colour information of six image channels (the RGB model and the HSI model) can be exhaustively extracted, which enhances the robustness of the algorithm. On the issue of improving the detection accuracy, the standard deviation is used to characterise the relationship of the colour information between the parts of DOCT coefficient matrix, and the K‐fold cross‐validation is introduced to improve the identification performance of the classifier. The steps of the algorithm are as follows: Firstly, the 8 × 8 block DOCT transform is used to the original image to obtain parts of block DOCT coefficient. Secondly, the standard deviation is used to process the corresponding parts of all blocks of the image. Finally, the Markov feature vector of the DOCT coefficient is extracted and feds to the LIBSVM (a library for support vector machines). When using LIBSVM for classification, K‐fold cross‐validation is executed to select the best parameter pairs. The experiment results demonstrate that the algorithm is superior to the other state‐of‐the‐art splicing detection methods.

Discrete octonion Fourier transform and the analysis of discrete 3-D data

“…One could ask the question why it is worth working in two different algebras in parallel instead of just working in the algebra of quadruple-complex numbers F. While going through calculations in F facilitates the interpretation of results, there are more and more papers in the literature devoted to the use of octonion algebra (Gao and Lam 2014;Grigoryan and Agaian 2018;Hahn and Snopek 2016;Klco et al 2017;Lazendić et al 2018a, b;Lian 2019;Popa 2016Popa , 2018Sheng et al 2018;Snopek 2015;Wang et al 2017). Therefore, it seems important to develop tools enabling work in this algebra as well.…”

“…The area of applications is focused so far on the study of neural networks (Popa 2016(Popa , 2018, analysis of color and multispectral images (Ell et a. 2014;Gao and Lam 2014;Gomes et al 2017;Grigoryan and Agaian 2018;Lazendić et al 2018a, b;Sheng et al 2018), as well as the biomedical signals processing (Delsuc 1988;Klco et al 2017).…”

Predicting image credibility in fake news over social media using multi-modal approach

“…Other novel methods like multiscale WLD histograms [18] and fractional Zernike moments (FrZms) [19] are also used. Similarly, for identifying image splicing CFA [20,21], discrete octonion cosine transforms (DOCT) [22], and histograms gradients [23,24] are applied. The problem with forensic techniques is that each technique is suitable for individual manipulation type.…”

Efficient hybrid passive method for the detection and localization of copy-move and spliced images

“…El-Alfy et al [7] extracted Markov features in the DCT domain for forgery detection. Sheng et al [8] detected splicing by extracting Markov features in the discrete octonion cosine transform (DOCT) domain using a support vector machine (SVM) classifier.…”

“…Further, Figure 10 shows the comparison of receiver operating characteristics (ROC) curves for CASIA v1.0, [8] 98.77 ---Lamba [10] 99.65 ---Prakash [1] 99 [8] 97.59 ---Lamba [10] 99.01 ---Prakash [1] 96 [22] 96.60 ---Muhammad [23] 96.39 ---Agarwal [6] 93.81 ---Alahmadi [3] 97.77 ---Proposed method 98.17 98.21 98.11 96.33 "-" indicates not calculated by the author observed that the ROC curve of the proposed algorithm is closer to the upper left corner, which depicts that it attains a better accuracy rate in comparison to the existing schemes.…”