Digital Camera Identification Research Articles

Improving the reliability of digital camera identification by optimizing the algorithm for comparing noise signatures

Improving the reliability of digital camera identification by optimizing the algorithm for comparing noise signatures

Identifying the Digital Camera from Natural Images Using Residual Noise and the Jensen–Shannon Divergence

Regarding the problem of digital camera identification, many methods have been proposed, and for several of them, their effectiveness has been verified on the basis of disputed flat images. However, in real cases the disputed images are natural images, rather than flat images. In that case, several of the already proposed methods are not effective. Hence, in this paper, a method is proposed for the digital camera identification from natural images based on the statistical comparison between the residual noise in the natural disputed images and the fingerprint defined for the eligible digital cameras. In the reported case studies, the HDR database provided by the Communications and Signal Processing Laboratory of University of Florence is used to select a set of eligible digital cameras, and from this image database, for each digital camera, a set of disputed flat images, a set of disputed natural images, and a set of flat reference images were selected. Thus, the fingerprint of each digital camera was calculated from the probability density function (PDF) of the photo-response nonuniformity (PRNU) extracted from its reference images. Therefore, in order to identify the source digital camera of a natural disputed image, the Jensen–Shannon divergence (JSD) was implemented to statistically compare the PRNU-based fingerprint of each eligible source camera against the noise residual of that disputed image. The proposed method has a similar effectiveness to methods based on the peak-to-correlation energy or the Kullback–Leibler divergence when the disputed images are flat images and the PRNU is considered, but it is significantly more effective than those methods when the disputed images are natural images.

Deep Feature Learning for Intrinsic Signature Based Camera Discrimination

In this paper we consider the problem of “end-to-end” digital camera identification by considering sequence of images obtained from the cameras. The problem of digital camera identification is harder than the problem of identifying its analog counterpart since the process of analog to digital conversion smooths out the intrinsic noise in the analog signal. However it is known that identifying a digital camera is possible by analyzing the camera's intrinsic sensor artifacts that are introduced into the images/videos during the process of photo/video capture. It is known that such methods are computationally intensive requiring expensive pre-processing steps. In this paper we propose an end-to-end deep feature learning framework for identifying cameras using images obtained from them. We conduct experiments using three custom datasets: the first containing two cameras in an indoor environment where each camera may observe different scenes having no overlapping features, the second containing images from four cameras in an outdoor setting but where each camera observes scenes having overlapping features and the third containing images from two cameras observing the same checkerboard pattern in an indoor setting. Our results show that it is possible to capture the intrinsic hardware signature of the cameras using deep feature representations in an end-to-end framework. These deep feature maps can in turn be used to disambiguate the cameras from each another. Our system is end-to-end, requires no complicated pre-processing steps and the trained model is computationally efficient during testing, paving a way to have near instantaneous decisions for the problem of digital camera identification in production environments. Finally we present comparisons against the current state-of-the-art in digital camera identification which clearly establishes the superiority of the end-to-end solution.

Analysis of Skin disease techniques using Smart Phone and Digital Camera Identification of Skin Disease

Skin diseases are a serious health issue that affects a large number of individuals. In recent years, with the fast advancement of technology and the use of various data mining approaches, dermatological predictive classification has become increasingly predictive and accurate. It is more help to dermatologist to identify the disease, As a result, the development of machine learning approaches capable of efficiently. The purpose of this study is making an application of identification skin disease images by using the machines learning method, Support Vector Machine (SVM), and KNN techniques. The image processes and machine learning is performed early detection of skin diseases. The aim of this study is determined the classification of skin diseases in humans. Each skin disease has symptoms. It has five skin diseases such as Acne, Psoriasis, Wrath, Psoriasis, and Ulcer. We have collected 314 skin disease images from the government of hospital, Aurangabad with the help of mobile camera and Sony HD camera. Gaussian Filter is used for image pre-processing. The segmentation method is used for K-Means Clustering and the feature extraction method are used for feature extraction. We have used Haar feature, color feature, FCM, OS-FCM, GLCM and LBF features for classifications. Based on the result, the SVM is given 92% accuracy for haar feature, FCM and OS-FCM. and KNN classifier, K-Means are given 89% and 89% accuracy using mobile phone camera dataset. The SVM, KNN and K-Means are given 91%, 87% and 89% accuracy respectively using Sony HD camera dataset. SVM is given good result in both dataset.

Digital camera identification by fingerprint’s compact representation

Digital camera identification by fingerprint’s compact representation

Robustness of digital camera identification with convolutional neural networks

This paper considers the area of digital forensics (DF). One of the problem in DF is the issue of identification of digital cameras based on images. This aspect has been attractive in recent years due to popularity of social media platforms like Facebook, Twitter etc., where lots of photographs are shared. Although many algorithms and methods for digital camera identification have been proposed, there is lack of research about their robustness. Therefore, in this paper the robustness of digital camera identification with the use of convolutional neural network is discussed. It is assumed that images may be of poor quality, for example, degraded by Poisson noise, Gaussian blur, random noise or removing pixels’ least significant bit. Experimental evaluation conducted on two large image datasets (including Dresden Image Database) confirms usefulness of proposed method, where noised images are recognized with almost the same high accuracy as normal images.

A feature-based approach for digital camera identification using photo-response non-uniformity noise

Source camera identification of an image is an emerging field of digital forensics. To identify the source camera through which the image is captured, photo-response non-uniformity (PRNU) noise is used as a camera fingerprint, as it is a unique characteristic that distinguishes images taken from the similar cameras. This paper presents a feature-based approach to identify the source camera. The input image is denoised using the denoising filter and from this denoised image, PRNU noise pattern is extracted. These PRNU noise patterns are represented by Hu's invariants, which are perpetual under image scaling, translation and rotation. These features are fed to fuzzy min-max neural network (FMNN) for training and classification for digital camera identification. The proposed approach has the ability to identify the cameras capturing the same scene.

A feature-based approach for digital camera identification using photo-response non-uniformity noise

A feature-based approach for digital camera identification using photo-response non-uniformity noise

On robustness of camera identification algorithms

In this paper we consider the problem of a privacy threat enabling tracing digital cameras by the analysis of pictures they produced. As thousands of images are processed at a mass scale, the threat may apply to most users of digital cameras. We consider a state-of-the-art algorithm for digital camera identification proposed in Lucas et al. (IEEE Trans Inf Forensics Secur 1(2):205–214, 2006) and discuss strategies that can be used to bypass it, in order to make information about the camera unavailable. It turns out that many natural strategies like Gaussian blur, adding artificial noise or removing pixels’ least significant bit from the image does not prevent the identification of a camera unless a huge loss of image details is suffered. On the other hand, we show a method to bypass the camera identification with a just marginally more complex, yet not intuitive, method namely cropping the image on the edges and resizing to the original size using Lanczos resampling.

Digital camera identification based on analysis of optical defects

In this paper we deal with the problem of digital camera identification by photographs. Identifying camera is possible by analyzing camera’s sensor artifacts that occur during the process of photo processing. The problem of digital camera identification has been popular for a long time. Recently many effective and robust algorithms for solving this problem have been proposed. However, almost all solutions are based on state-of-the-art algorithm, proposed by Lukás et al. in 2006. Core of this algorithm is to calculate the so-called sensor pattern noise based on denoising images with wavelet-based denoising filter. Such technique is very efficient, but very time consuming. In this paper we consider tracing cameras by analyzing defects of their optical systems, like vignetting and lens distortion. We show that analysis of vignetting defect allows for recognizing brand of the camera. Lens distortion can be used to distinguish images from different cameras. Experimental evaluation was carried out on 60 devices (compact cameras and smartphones) for a total number of 12 051 images, with support of the Dresden Image Database. Proposed methods do not require denoising images with wavelet-based denoising filter what has a significant influence for speed of image processing, compared with state-of-the-art algorithm.

Camera-identification and common-source identification: The correlation values of mismatches

A robust and well-known way to identify the source of an image is the use of Photo Response Non-Uniformity. The ability to be able to extract the PRNU-pattern from images is both used for camera-identification (linking one or more images to a camera) and common-source identification (linking images to images). In this paper we focus on the correlation values of mismatches, i.e. the correlation between images made with different cameras. Although the correlation values of mismatches are close to zero, they are never exactly zero. In this paper we show that it is possible with an extremely simple formula to a priori estimate the typical range for mismatch correlation values. This simple formula can be used as a decision rule in digital camera identification to either perform a complete investigation including reference recordings (which is time consuming) or not. In common-source identification this simple formula can be used to provide a well-educated guess for the threshold value to the cluster algorithm instead of just arbitrarily trying a range of threshold values.

Digital camera identification using PRNU: A feature based approach

Source camera identification is one of the emerging field in digital image forensics, which aims at identifying the source camera used for capturing the given image. The technique uses photo response non-uniformity (PRNU) noise as a camera fingerprint, as it is found to be one of the unique characteristic which is capable of distinguishing the images even if they are captured from similar cameras. Most of the existing PRNU based approaches are very sensitive to the random noise components existing in the estimated PRNU, and also they are not robust when some simple manipulations are performed on the images. Hence a new feature based approach of PRNU is proposed for the source camera identification by choosing the features which are robust for image manipulations. The PRNU noise is extracted from the images using wavelet based denoising method and is represented by higher order wavelet statistics (HOWS), which are invariant features for image manipulations and geometric variations. The features are fed to support vector machine classifiers to identify the originating source camera for the given image and the results have been verified by performing ten-fold cross validation technique. The experiments have been carried out using the images captured from various cell phone cameras and it demonstrated that the proposed algorithm is capable of identifying the source camera of the given image with good accuracy. The developed technique can be used for differentiating the images, even if they are captured from similar cameras, which belongs to same make and model. The analysis have also showed that the proposed technique remains robust even if the images are subjected to simple manipulations or geometric variations.

Sensor Pattern Noise Estimation Using Probabilistically Estimated RAW Values

Photo response nonuniformity (PRNU) is consider as reliable camera fingerprint for identifying source of a digital images. Digital cameras use various image processing operations to map linear color measurements (raw data) into nonlinear narrow gamut image. This nonlinear transformation affects estimation of PRNU. To undo the effect of nonlinear transformation, in this letter, we propose to estimate PRNU from probabilistically obtained raw values. Since not all cameras provide raw values as their output, we propose to compute estimate of raw values from the JPEG images using probabilistic color derendering procedure. The estimated raw values are modeled as a Poisson process and then maximum likelihood estimation (MLE) is used for PRNU estimation. The experimental results show that, the digital camera identification using our proposed PRNU estimate is better than using other popular PRNU estimate.

Advance Feature Extraction Technique for Digital Camera Identification

On the World Wide Web, a large amount of image content is distributed, owing to the rapid progress in digital camera technologies. For presenting evidence in a court and helping police investigations Digital camera identification, which is the identification of the source camera of input image is becoming increasingly important. A digital camera identification method using the image sensor’s pattern noise has received considerable attention in recent years. The existence of differences between the sensitivities of pixels Photo-response nonuniformity (PRNU) noise is mainly generated and it is useful as a fingerprint of a camera. By image processing engine, however the PRNU noise of an image is usually contaminated by random noise and scene content affected by the image processing engine, which inhibits stable Identification. The pairwise magnitude relations of image sensor noise, we proposed a novel digital camera identification method using, which are robust to noise contamination. That the proposed method can identify the source cameras of query images with high accuracy we demonstrate, by performing experiments.

Common source identification of images in large databases

Photo-response non-uniformity noise patterns are a robust way to identify the source of an image. However, identifying a common source of images in a large database may be impractical due to long computation times. In this paper a solution for large volume digital camera identification is proposed, which combines, and sometimes slightly modifies, existing methods for a 500 times improvement in the speed of common source identification. Single image comparisons are often plagued by considerable noise contamination from scene content and random noise, which makes it harder to accomplish reliable common source identification. Therefore a new method is introduced that can increase true positive rates by more than 45% at very low computation costs. Analysis of real data from a fraud case shows the effectiveness of the proposed method. As a whole the proposed solution makes it possible to analyze a large database in forensically relevant time, without resorting to large and expensive computer clusters.

Hardware Architecture for Video Authentication Using Sensor Pattern Noise

Digital camera identification can be accomplished based on sensor pattern noise, which is unique to a device, and serves as a distinct identification fingerprint. Camera identification and authentication have formed the basis of image/video forensics in legal proceedings. Unfortunately, real-time video source identification is a computationally heavy task, and does not scale well to conventional software implementations on typical embedded devices. In this paper, we propose a hardware architecture for source identification in networked cameras. The underlying algorithms, an orthogonal forward and inverse discrete wavelet transform and minimum mean square error-based estimation, have been optimized for 2-D frame sequences in terms of area and throughput performance. We exploit parallelism, pipelining, and hardware reuse techniques to minimize hardware resource utilization and increase the achievable throughput of the design. A prototype implementation on a Xilinx Virtex-6 FPGA device was optimized with a resulting throughput of 167 MB/s, processing 30 640 × 480 video frames in 0.17 s.

Robust Digital Camera Identification Based on Pairwise Magnitude Relations of Clustered Sensor Pattern Noise

Owing to the rapid progress in digital camera technologies, a large amount of image content is distributed on the World Wide Web. Digital camera identification, which is the identification of the source camera of an input image, is becoming increasingly important for presenting evidence in a court and helping police investigations. In recent years, a digital camera identification method using the image sensor's pattern noise has received considerable attention. Photo-response non-uniformity (PRNU) noise is mainly generated by the existence of differences between the sensitivities of pixels, and it is useful as a fingerprint of a camera. However, the PRNU noise of an image is usually contaminated by random noise and scene content and affected by the image processing engine, which inhibits stable identification. In this paper, we propose a novel digital camera identification method using the pairwise magnitude relations of image sensor noise, which are robust to noise contamination. By performing experiments, we demonstrate that the proposed method can identify the source cameras of query images with high accuracy.

Improving source camera identification using a simplified total variation based noise removal algorithm

In this paper a new method for photo-response non-uniformity (PRNU) noise extraction is proposed. Photo-response non-uniformity noise patterns are a reliably method for digital camera identification. Especially with a large number of images the process of camera identification can be time consuming. The proposed method aims to increase the speed of PRNU extraction without losing accuracy when compared to the state-of-the-art method. Currently wavelet based denoising is used as the standard for PRNU extraction. Our proposed method is based on a simplified version of the Total Variation based noise removal algorithm. Results show that extraction is about 3.5 times faster with our method than with the wavelet based denoising algorithm. While initially only an increase in speed was the goal, results indicate that the Total Variation based noise removal algorithm is not only faster, but also more accurate than the state-of-the-art method.

A confidence map and pixel-based weighted correlation for PRNU-based camera identification

In this paper, we propose a confidence map and a pixel-based weighted correlation method for digital camera identification. In traditional camera identification method, a simple denoising technique is used to extract the photo-response non-uniformity (PRNU) as the difference between the original image and the denoised image. One of the major problems is that the image content is left behind in the noise residue which affects the correlation calculation for identifying the source camera. In order to solve the problem, we first study the image content effect by examining the effect of different image features on correlation. We then formulate the image content effect by nonlinear regression model and apply this relationship to obtain a confidence map for the testing images. In such way, the confidence map shows the reliability of each pixel in correlation calculation. It can be used as a weighting function so as to give a higher weighting to pixel which is more reliable and a lower weighting for less reliable pixel. By using the weighted correlation, our proposed method is able to improve the identification accuracies especially for the low quality image such as heavy JPEG compression. In particular, we found 5–20% improvement in identification accuracy at JPEG quality factor of 70.

Assessment of Approximate Likelihood Ratios from Continuous Distributions: A Case Study of Digital Camera Identification*

A reported likelihood ratio for the value of evidence is very often a point estimate based on various types of reference data. When presented in court, such frequentist likelihood ratio gets a higher scientific value if it is accompanied by an error bound. This becomes particularly important when the magnitude of the likelihood ratio is modest and thus is giving less support for the forwarded proposition. Here, we investigate methods for error bound estimation for the specific case of digital camera identification. The underlying probability distributions are continuous and previously proposed models for those are used, but the derived methodology is otherwise general. Both asymptotic and resampling distributions are applied in combination with different types of point estimators. The results show that resampling is preferable for assessment based on asymptotic distributions. Further, assessment of parametric estimators is superior to evaluation of kernel estimators when background data are limited.