A forensic algorithm against median filtering based on coefficients of image blocks in frequency domain

Wang, Dongping; Gao, Tiegang; Yang, Fusheng

doi:10.1007/s11042-018-5651-z

Cited by 12 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results show that the proposed detector is robust for a combination of low‐resolution and moderate JPEG quality factors. In a recent work [17], image discrete cosine transform (DCT) sub‐band coefficients are utilised as fingerprints for median filtering detection. The method works well for low‐resolution images with a large feature set of variable length, which varies according to the image size.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In recent works, intrinsic fingerprints have been extracted in terms of hand‐crafted features and convolutional neural network (CNN)‐based features. Hand‐crafted features based detectors are mainly developed for detection of image resampling [2], JPEG compression [3], contrast enhancement [4, 5], median filtering [6–17] and multiple manipulations [18]. However, recent CNN‐based detectors have focused on median filtering detection [19, 20] and multiple manipulation detections [21, 22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Global median filtering forensic method based on Pearson parameter statistics

Gupta

Singhal

2019

IET image process

View full text Add to dashboard Cite

Median filtering forensics in images is a subject under intense study nowadays. Existing median filtering detectors are developed based on hand‐crafted features and convolutional neural networks (CNN). Among hand‐crafted features based detectors, most of the detector's performance deteriorate for low‐resolution images compressed with low‐quality factors. However, CNN‐based detectors are found to be more robust at the expense of large database and large training time requirement. In this study, the authors propose a robust median filtering detector by exploiting the statistics of the Pearson parameter κ, κ is defined as the polynomial ratio of skewness and kurtosis. To capture fingerprints of median filtering, κ is determined for the median filtered residual (MFR) of the images to construct a novel feature set of 23 dimensions. The efficacy of the proposed feature set, against existing hand‐crafted features based and CNN‐based detectors, is established by a series of experiments for global median filtering detection. Results reveal that the proposed feature set exhibits performance gain of 2–4% against existing hand‐crafted features based detectors and an approximate gain of 4% against CNN‐based detector for detection of low‐resolution median filtered images compressed with low‐quality factors.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Global median filtering forensic method based on Pearson parameter statistics

Gupta

Singhal

2019

IET image process

View full text Add to dashboard Cite

show abstract

“…Previous researchers offered a lot of contribution for MF forensics. There exist three categories of MF forensic methods, i.e., threshold-based methods [10], [11], SVM-based methods [12]- [19], and CNN-based methods [20]- [23]. In the threshold-based methods, Kirchner and Fridrich [10] invented an image feature derived from histogram bins of the first-order difference image.…”

Section: Introductionmentioning

confidence: 99%

“…Motivated by the work in [15], Yang et al [18] combined the 2-D AR coefficients of median filtered residual (MFR), average filtered residual (AFR), and gaussian filtered residual (GFR). Wang et al [19] used the coefficients in image frequency domain as a feature set. The SVM-based methods are more robust than the threshold-based methods when dealing with small size and JPEG compressed MF images.…”

Section: Introductionmentioning

confidence: 99%

Robust Median Filtering Forensics Using Image Deblocking and Filtered Residual Fusion

Shan

Qiu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Median filtering (MF) is frequently applied to conceal the traces of forgery and therefore can provide indirect forensic evidence of tampering when investigating composite images. The existing MF forensic methods, however, ignore how JPEG compression affects median filtered images, resulting in heavy performance degradation when detecting filtered images stored in the JPEG format. In this paper, we propose a new robust MF forensic method based on a modified convolutional neural network (CNN). First, relying on the analysis of the influence on median filtered images caused by JPEG compression, we effectively suppress the interference using image deblocking. Second, the fingerprints left by MF are highlighted via filtered residual fusion. These two functions are fulfilled with a deblocking layer and a fused filtered residual (FFR) layer. Finally, the output of the FFR layer becomes input when extracting multiple features for further classification using a tailor-made CNN. The extensive experimental results show that the proposed method outperforms the state-of-the-art methods in both JPEG compressed and small-sized MF image detection. INDEX TERMS Median filtering, convolutional neural networks, robust forensics, JPEG compression, image deblocking.

show abstract

“…It can detect median filtering in the cases of JPEG compression and low resolution. Some works [8], [9] exploited the median filtering fingerprints in frequency domain and achieved excellent results in the median filtering forensics.…”

Section: Introductionmentioning

confidence: 99%

Median Filtering Forensics Using Multiple Models in Residual Domain

et al. 2019

View full text Add to dashboard Cite

Median filtering, due to highly non-linear and content-preserving, has widely used in the multimedia security fields, such as anti-forensics, steganography, and steganalysis. In the past decade, many excellent algorithms have been proposed, and have solved median filtering forensics perfectly for images without post-processing. However, it is still a challenging task when the test images are of low resolution and post-processed by lossy JPEG compression. Moreover, in order to meet the requirements of detecting forgery from the massive image database in the social network, a fast and efficient detector is needed. In this paper, we present an improved method for median filtering forensics in challenging problems, such as detecting median filtering from a heavily JPEG compressed image. To do this, we first investigate median filtering traces by a group of diverse residuals. These residuals not only eliminate influence from image contents but also highlight the traces from different aspects. We then construct a feature set on the residuals by incorporating the Markov chain model with the auto-regressive model. These two compensated models effectively reveal different relationships among neighboring residuals. For a fast detector, a series of dimension reduction methods are employed. The experimental results on a composite image database demonstrate that the proposed method outperforms prior arts when detecting median filtering in heavily JPEG compressed images as well as low-resolution images. INDEX TERMS Digital image forensics, median filtering forensics, auto-regressive model, Markov chain.

show abstract

A forensic algorithm against median filtering based on coefficients of image blocks in frequency domain

Cited by 12 publications

References 16 publications

Global median filtering forensic method based on Pearson parameter statistics

Global median filtering forensic method based on Pearson parameter statistics

Robust Median Filtering Forensics Using Image Deblocking and Filtered Residual Fusion

Median Filtering Forensics Using Multiple Models in Residual Domain

Contact Info

Product

Resources

About