Splicing Detection Research Articles

基于小波域上质量参数特征的图像拼接篡改盲检测

基于小波域上质量参数特征的图像拼接篡改盲检测

Enhancement of Media Splicing Detection: A General Framework

Enhancement of Media Splicing Detection: A General Framework

Quaternion pseudo-Zernike moments combining both of RGB information and depth information for color image splicing detection

The quaternion representation (QR) used in current quaternion-based color image processing creates redundancy when representing a color image of three components by a quaternion matrix having four components. In this paper, both RGB and depth (RGB-D) information are considered to improve QR for efficiently representing RGB-D images. The improved QR fully utilizes the four-dimensional quaternion domain. Using this improved QR, firstly we define the new quaternion pseudo-Zernike moments (NQPZMs) and then propose an efficient computational algorithm for NQPZMs through the conventional pseudo-Zernike moments (PZMs). Finally, we propose an algorithm for color image splicing detection based on the NQPZMs and the quaternion back-propagation neural network (QBPNN). Experimental results on four public datasets (DVMM, CASIA v1.0 and v2.0, Wild Web) demonstrate that the proposed splicing detection algorithm can achieve almost 100% accuracy with the appropriate feature dimensionality and outperforms 14 existing algorithms. Moreover, the comparison of six color spaces (RGB, HSI, HSV, YCbCr, YUV, and YIQ) shows that the proposed algorithm using YCbCr color space has the overall best performance in splicing detection.

A computational integrative approach based on alternative splicing analysis to compare immortalized and primary cancer cells.

Immortalized cell lines are widely used to study the effectiveness and toxicity of anti cancer drugs as well as to assess the phenotypic characteristics of cancer cells, such as proliferation and migration ability. Unfortunately, cell lines often show extremely different properties than tumor tissues. Also the primary cells, that are deprived of the in vivo environment, might adapt to artificial conditions, and differ from the tissue they should represent. Despite these considerations, cell lines are still one of the most used cancer models due to their availability and capability to expand without limitation, but the clinical relevance of their use is still a big issue in cancer research. Many studies tried to overcome this task, comparing cell lines and tumor samples through the definition of the genomic and transcriptomic differences. To this aim, most of them used nucleotide variation or gene expression data. Here we introduce a different strategy based on alternative splicing detection and integration of DNA and RNA sequencing data, to explore the differences between immortalized and tissue-derived cells at isoforms level. Furthermore, in order to better investigate the heterogeneity of both cell populations, we took advantage of a public available dataset obtained with a new simultaneous omics single cell sequencing methodology. The proposed pipeline allowed us to identify, through a computational and prediction approach, putative mutated and alternative spliced transcripts responsible for the dissimilarity between immortalized and primary hepato carcinoma cells.

Comprehensive RNA-seq transcriptomic profiling in the malignant progression of gliomas

Gliomas are the most common and lethal intracranial tumours. RNA sequencing technologies and advanced data analyses recently enabled the characterization of transcriptomic information, including protein-coding gene expression, non-coding gene expression, alternative splicing, and fusion gene detection, to facilitate detection of diseases and altered phenotypes. As a part of the Chinese Glioma Genome Atlas (CGGA) project, our aim was to delineate comprehensive transcriptome profiling in the malignant progression of human gliomas. Three hundred twenty five gliomas with different grades were collected over the past twelve years. Using the Illumina HiSeq 2,000 system, over 92 million high quality 101-bp paired-end reads were generated per sample, yielding a total of 30 billion reads. This comprehensive dataset will be useful to deepen the comprehensive understanding of gliomas, providing an opportunity to generate new therapies, diagnoses, and preventive strategies.

Detecting blurred image splicing using blur type inconsistency

In a tampered blurred image generated by splicing, the spliced region and the original image may have different blur types. Splicing detection in this image is a challenging problem. In recent years, researchers have proposed various methods for detecting such splicing. In this paper, we propose a novel framework for image splicing detection based on partial blur type inconsistency. In this framework, after the cepstrum-based image transforming, a blur type classification parameter is extracted from the spectrum characteristics of spliced blurred image. The blurred image is restored based on the blur kernel which is constructed by estimating the blur parameters. Finally, a fine measure method is applied to segmentation inconsistent region in restored images that contain large amounts of ringing effect. Simulation results show the proposed method effectiveness in detecting forgery part in spliced images with different blur types. The proposed method has good robustness against lossy JPEG compression and noising, which outperforms the state-of-the-art methods for small spliced regions.

Splicing image forgery detection using textural features based on the grey level co‐occurrence matrices

To further improve the detection rate with relatively low dimension feature vector, a novel passive splicing detection method using textural features based on the grey level co-occurrence matrices, namely TF-GLCM, is proposed in this study. In the TF-GLCM, the GLCM are calculated based on the difference block discrete cosine transform arrays to capture the textural information and the spatial relationship between image pixels sufficiently. The discriminable properties contained in the GLCM are described by six textural features, which include two new introduced ones and four independent ones. In addition, the statistical moments mean Me and standard deviation SD of textural features are used instead of themselves as elements in feature vector to reduce the dimensionality of feature vector and computational complexity. A support vector machine is employed for classification purpose. Experimental results show that the TF-GLCM achieves the detection rates of 98% on CASIA v1.0, and 97% on CASIA v2.0 with 96-D feature vector. The detection rates benefit from the two new textural features. Meanwhile, the TF-GLCM is superior to some state-of-the-art methods with lower dimension feature vector.

Erratum to: Statistically based splicing detection reveals neural enrichment and tissue-specific induction of circular RNA during human fetal development.

In this version of this article that was originally published [1] the authors had analysed two HeLa samples, SRR1637089 and SRR1637090, in Fig. 3 of the original publication. The authors had respectively analysed the samples as RNaseR+ and Ribominus, due to their incorrect annotations in a public database, but they were both Ribominus samples. The authors have now analysed appropriate positive and negative controls using their method, KNIFE, and find_circ. The results are presented in an amended version of Fig. 3c, please see updated version below. Furthermore, the authors have now provided a list of accession codes for the ENCODE data they analysed, please see the Table 1 below. Please note this was not part of the original article. Source (cell line name or tissue type), Type of sample (tissue, polyA+ cell line, or polyA- cell line), and Accession code for all ENCODE data analyzed.]

Reliability assessment of principal point estimates for forensic applications

Although quite recent as a forensic research domain, computer vision analysis of scenes is likely to become more and more important in the near future, thanks to its robustness to image alterations at the signal level, such as image compression and filtering. However, the experimental assessment of vision-based forensic algorithms is a particularly critical task, since they cannot be tested on massive amounts of data, and their performance can heavily depend on user skill. In this paper we investigate on the accuracy and reliability of a vision-based, user-supervised method for the estimation of the camera principal point, to be used in cropping and splicing detection. Results of an extensive experimental evaluation show how the estimation accuracy depends on perspective conditions as well as on the selected image features. Such evidence led us to define a novel visual feature, referred to as Minimum Vanishing Angle, which can be used to assess the reliability of the method.

Image splicing detection based on Markov features in QDCT domain

Image splicing is very common and fundamental in image tampering. Therefore, image splicing detection has attracted more and more attention recently in digital forensics. Gray images are used directly, or color images are converted to gray images before be processed in previous image splicing detection algorithms. However, most forgery images are color images. In order to make use of the color information in images, a classification algorithm is put forward which can use color images directly. In this paper, an algorithm based on Markov in quaternion discrete cosine transform (QDCT) domain is proposed for image splicing detection. First of all, color information is extracted from blocked images to construct quaternion in a whole manner, and the QDCT coefficients of quaternion blocked images can be obtained. Secondly, the expanded Markov features generated from the transition probability matrices in QDCT domain can not only capture the intra-block, but also the inter-block correlation between block QDCT coefficients. Finally, support vector machine (SVM) is exploited to classify the Markov feature vector. The experiment results demonstrate that the proposed algorithm not only make use of color information of images, but also can yield considerably better detection performance compared with the state-of-the-art splicing detection methods tested on the same dataset.

Dynamic ASXL1 Exon Skipping and Alternative Circular Splicing in Single Human Cells.

Circular RNAs comprise a poorly understood new class of noncoding RNA. In this study, we used a combination of targeted deletion, high-resolution splicing detection, and single-cell sequencing to deeply probe ASXL1 circular splicing. We found that efficient circular splicing required the canonical transcriptional start site and inverted AluSx elements. Sequencing-based interrogation of isoforms after ASXL1 overexpression identified promiscuous linear splicing between all exons, with the two most abundant non-canonical linear products skipping the exons that produced the circular isoforms. Single-cell sequencing revealed a strong preference for either the linear or circular ASXL1 isoforms in each cell, and found the predominant exon skipping product is frequently co-expressed with its reciprocal circular isoform. Finally, absolute quantification of ASXL1 isoforms confirmed our findings and suggests that standard methods overestimate circRNA abundance. Taken together, these data reveal a dynamic new view of circRNA genesis, providing additional framework for studying their roles in cellular biology.

Image splicing detection based on inter-scale 2D joint characteristic function moments in wavelet domain

In this paper, we propose an image splicing detecting method using the characteristic function moments for the inter-scale co-occurrence matrix in the wavelet domain. We construct the co-occurrence matrices by using a pair of wavelet difference values across inter-scale wavelet subbands. In this process, we do not adopt the thresholding operation to prevent information loss. We extract the high-order characteristic function moments of the two-dimensional joint density function generated by the inter-scale co-concurrent matrices in order to detect image splicing forgery. Our method can be applied regardless of the color or gray image dataset using only luminance component of an image. By performing experimental simulations, we demonstrate that the proposed method achieves good performance in splicing detection. Our results show that the detection accuracy was greater than 95 % on average with well-known four splicing detection image datasets.

Audio splicing detection and localization using environmental signature

Audio splicing is one of the most common manipulation techniques in the area of audio forensics. In this paper, the magnitudes of acoustic channel impulse response and ambient noise are proposed as the environmental signature. Specifically, the spliced audio segments are detected according to the magnitude correlation between the query frames and reference frames via a statically optimal threshold. The detection accuracy is further refined by comparing the adjacent frames. The effectiveness of the proposed method is tested on two data sets. One is generated from TIMIT database, and the other one is made in four acoustic environments using a commercial grade microphones. Experimental results show that the proposed method not only detects the presence of spliced frames, but also localizes the forgery segments with near perfect accuracy. Comparison results illustrate that the identification accuracy of the proposed scheme is higher than the previous schemes. In addition, experimental results also show that the proposed scheme is robust to MP3 compression attack, which is also superior to the previous works.

Joint image splicing detection in DCT and Contourlet transform domain

Splicing is a fundamental and popular image forgery method and image splicing detection is urgently called for digital image forensics recently. In this paper, a Markov based approach is proposed to detect image splicing. The paper applies the Markov model in the block discrete cosine transform (DCT) domain and the Contourlet transform domain. First, the original Markov features of the inter-block between block DCT coefficients are improved by considering the different frequency ranges of each block DCT coefficients. Then, additional features are extracted in Contourlet transform domain to characterize the dependency of positions among Contourlet subband coefficients. And these features are extracted from single color channel for gray image while extracted from three color channels for color image. Finally, Support Vector Machines (SVMs) are exploited to classify the authentic and spliced images for the gray image dataset while ensemble classifier to the color image dataset. The experiment results demonstrate that the proposed detection scheme outperforms some state-of-the-art methods when applied to Columbia Image Splicing Detection Evaluation Dataset (DVMM), and ranks fourth in phase 1 on the Live Ranking of the first Image Forensics Challenge.

Anti-Forensics of Environmental-Signature-Based Audio Splicing Detection and Its Countermeasure via Rich-Features Classification

Numerous methods for detecting audio splicing have been proposed. Environmental-signature-based methods are considered to be the most effective forgery detection methods. The performance of existing audio forensic analysis methods is generally measured in the absence of any anti-forensic attack. Effectiveness of these methods in the presence of anti-forensic attacks is therefore unknown. In this paper, we propose an effective anti-forensic attack for environmental-signature-based splicing detection method and countermeasures to detect the presence of the anti-forensic attack. For anti-forensic attack, dereverberation-based processing is proposed. Three dereverberation methods are considered to tamper with the acoustic environment signature. Experimental results indicate that the proposed dereverberation-based anti-forensic attack significantly degrades the performance of the selected splicing detection method. The proposed countermeasures exploit artifacts introduced by the anti-forensic processing. To detect the presence of potential anti-forensic processing, a machine learning-based framework is proposed. In particular, the proposed anti-forensic detection method uses a rich-feature model consisting of Fourier coefficients, spectral properties, high-order statistics of musical noise residuals, and modulation spectral coefficients to capture traces of dereverberation attacks. The performance of the proposed framework is evaluated on both synthetic data and real-world speech recordings. The experimental results show that the proposed rich-feature model can detect the presence of anti-forensic processing with an average accuracy of 95%.

Detecting Image Splicing Based on Noise Level Inconsistency

In a spliced image, areas from different origins contain different noise features, which may be exploited as evidence for forgery detection. In this paper, we propose a noise level evaluation method for digital photos, and use the method to detect image splicing. Unlike most noise-based forensic techniques in which an AWGN model is assumed, the noise distribution used in the present work is intensity-dependent. This model can be described with a noise level function (NLF) that better fits the actual noise characteristics. NLF reveals variation in the standard deviation of noise with respect to image intensity. In contrast to denoising problems, noise in forensic applications is generally weak and content-related, and estimation of noise characteristics must be done in small areas. By exploring the relationship between NLF and the camera response function (CRF), we fit the NLF curve under the CRF constraints. We then formulate a Bayesian maximum a posteriori (MAP) framework to optimize the NLF estimation, and develop a method for image splicing detection according to noise level inconsistency in image blocks taking from different origins. Experimental results are presented to show effectiveness of the proposed method.

SRRM4 Drives Neuroendocrine Transdifferentiation of Prostate Adenocarcinoma Under Androgen Receptor Pathway Inhibition

BackgroundNeuroendocrine prostate cancer (NEPC) is an aggressive subtype of castration-resistant prostate cancer that typically does not respond to androgen receptor pathway inhibition (ARPI), and its diagnosis is increasing. ObjectiveTo understand how NEPC develops and to identify driver genes to inform therapy for NEPC prevention. Design, setting, and participantsWhole-transcriptome sequencing data were extracted from prostate tumors from two independent cohorts: The Beltran cohort contained 27 adenocarcinoma and five NEPC patient samples, and the Vancouver Prostate Centre cohort contained three patient samples and nine patient-derived xenografts. InterventionA novel bioinformatics tool, comparative alternative splicing detection (COMPAS), was invented to analyze alternative RNA splicing on RNA-sequencing data. Outcome measurements and statistical analysisCOMPAS identified potential driver genes for NEPC development. Biochemical and biological validations were performed in both prostate cell and tumor models. Results and limitationMore than 66% of the splice events were predicted to be regulated by the RNA splicing factor serine/arginine repetitive matrix 4 (SRRM4). In vitro and in vivo evidence confirmed that one SRRM4 target gene was the RE1 silencing transcription factor (REST), a master regulator of neurogenesis. Moreover, SRRM4 strongly stimulated adenocarcinoma cells to express NEPC biomarkers, and this effect was exacerbated by ARPI. ARPI combined with a gain of SRRM4-induced adenocarcinoma cells to assume multicellular spheroid morphology and was essential in establishing progressive NEPC xenografts. These SRRM4 actions were further enhanced by loss of function of TP53. ConclusionsSRRM4 drives NEPC progression. This knowledge may guide the development of novel therapeutics aimed at NEPC. Patient summaryUsing next-generation RNA sequencing and our newly developed bioinformatics tool, we identified a neuroendocrine prostate cancer (NEPC)–specific RNA splicing signature that is predominantly controlled by serine/arginine repetitive matrix 4 (SRRM4). We confirmed that SRRM4 drives NEPC progression, and we propose SRRM4 as a potential therapeutic target for NEPC.

접합 영상 검출을 위한 마르코프 천이 확률 및 동시발생 확률에 대한 선택적 특징 추출 방법

ABSTRACT In this paper, we propose a selective feature extraction algorithm between Markov transition probability and co-occurrence probability for an effective image splicing detection. The Features used in our method are composed of the difference values between DCT coefficients in the adjacent blocks and the value of Kullback-Leibler divergence(KLD) is calculated to evaluate the differences between the distribution of original image features and spliced image features. KLD value is an efficient measure for selecting Markov feature or Co-occurrence feature because KLD shows non-similarity of the two distributions. After training the extracted feature vectors using the SVM classifier, we determine whether the presence of the image splicing forgery. To verify our algorithm we used grid search and 6-folds cross-validation. Based on the experimental results it shows that the proposed method has good detection performance with a limited number of features compared to conventional methods.

Efficient Markov feature extraction method for image splicing detection using maximization and threshold expansion

We propose an efficient Markov feature extraction method for color image splicing detection. The maximum value among the various directional difference values in the discrete cosine transform domain of three color channels is used to choose the Markov features. We show that the discriminability for slicing detection is increased through the maximization process from the point of view of the Kullback–Leibler divergence. In addition, we present a threshold expansion and Markov state decomposition algorithm. Threshold expansion reduces the information loss caused by the coefficient thresholding that is used to restrict the number of Markov features. To compensate the increased number of features due to the threshold expansion, we propose an even–odd Markov state decomposition algorithm. A fixed number of features, regardless of the difference directions, color channels and test datasets, are used in the proposed algorithm. We introduce three kinds of Markov feature vectors. The number of Markov features for splicing detection used in this paper is relatively small compared to the conventional methods, and our method does not require additional feature reduction algorithms. Through experimental simulations, we demonstrate that the proposed method achieves high performance in splicing detection.

Countering Noise-based Splicing Detection Using Noise Density Transfer

Image splicing is a common and widespread type of manipulation, which is defined as pasting a portion of an image onto a second image. Several forensic methods have been developed to detect splicing, using various image properties. Some of these methods exploit the noise statistics of the image to try and find discrepancies. In this paper, we propose a new counter-forensic approach to eliminate the noise differences that can appear in a spliced image. This approach can also be used when creating computer graphics images, in order to endow them with a realistic noise. This is performed by changing the noise statistics of the spliced elements so that they are closer to those of the original image. The proposed method makes use of a novel way to transfer density functions. We apply this to image noise in order to impose identical noise density functions from a source to a destination image. This method can be used with arbitrary noise distributions. The method is tested against several noise-based splicing detection methods, in order to prove its efficacy.