Digital Image Forgery Research Articles

Medical image classification algorithm based on principal component feature dimensionality reduction

Abstract A detection technique of digital image forgery based on local descriptor of multi-resolution Weber was proposed on the basis of Weber’s Law pertinent to deficiencies such as low accuracy, weak adaptability and simplicity of current detection algorithm of digital image forgery. WLD feature was extracted from chrominance channel of images, and more characteristic quantities could be extracted compared with single resolution through introduction of multi-resolution; meanwhile, WLD histogram could be formed under different resolutions in directions of differential excitation and gradient through optimization of WLD parameters; then classification could be conducted with SVM. Experimental data indicates: WLD of multi-resolution has better detection result compared with single resolution, and WLD of multi-resolution has better detection performance in detection of splicing forgery images and copying–moving forgery images. Forgery detection experiment in many image data bases indicates: WLD of multi-resolution has better detection result compared with single resolution, and WLD of multi-resolution has better detection performance in detection of splicing forgery images and copying–moving forgery images.

New Texture Descriptor Based on Modified Fractional Entropy for Digital Image Splicing Forgery Detection.

Forgery in digital images is immensely affected by the improvement of image manipulation tools. Image forgery can be classified as image splicing or copy-move on the basis of the image manipulation type. Image splicing involves creating a new tampered image by merging the components of one or more images. Moreover, image splicing disrupts the content and causes abnormality in the features of a tampered image. Most of the proposed algorithms are incapable of accurately classifying high-dimension feature vectors. Thus, the current study focuses on improving the accuracy of image splicing detection with low-dimension feature vectors. This study also proposes an approximated Machado fractional entropy (AMFE) of the discrete wavelet transform (DWT) to effectively capture splicing artifacts inside an image. AMFE is used as a new fractional texture descriptor, while DWT is applied to decompose the input image into a number of sub-images with different frequency bands. The standard image dataset CASIA v2 was used to evaluate the proposed approach. Superior detection accuracy and positive and false positive rates were achieved compared with other state-of-the-art approaches with a low-dimension of feature vectors.

New and efficient blind detection algorithm for digital image forgery using homomorphic image processing

Digital image forgery detection is an important task in digital life as the image may be easily manipulated. This paper presents a novel blind tampering detection algorithm for images acquired from digital cameras and scanners. The algorithm is based on applying homomorphic image processing on each suspicious image to separate illumination from reflectance components. In natural images, it is known that the illumination component is approximately constant, while changes can be detected in tampered ones. Support Vector Machine (SVM) and Neural Network (NN) classifiers are used for classification of tampered images based on the illumination component, and their results are compared to obtain the best classifier performance. The Receiver Operating Characteristic (ROC) curve is used to depict the classifier performance. Three different color coordinate systems are tested with the proposed algorithm, and their results are compared to obtain the highest accuracy level. Joint Photographic Experts Group (JPEG) compressed images with different Quality Factors (QFs) are also tested with the proposed algorithm, and the performance of the proposed algorithm in the presence of noise is studied. The performance of the SVM classifier is better than that of the NN classifier as it is more accurate and faster. A 96.93% detection accuracy has been obtained regardless of the acquisition device.

REVIEW OF THE METHODS TO DETECT FORGERY IN DIGITAL IMAGES FOR INTELLECTUAL DECISION SUPPORT SYSTEMS BASE ON NOISE ANALYSIS

This article provides a review of the up-to-date methods on noise analysis to detect forgery in digital images, which are used as a source of data in decision support systems.

Region duplication detection based on hybrid feature and evaluative clustering

Digital image are easy to be tampered by the photo editing software. Therefore, digital image forensics which aims at validating the authenticity of the digital image are received wide public concern. Region duplication is a commonly used operation in digital image forgeries. The main aims of the region duplication are to overemphasize or conceal some contents by duplicating some regions on the image. Most of the region duplication methods can be categorized into two main classes:block-based and keypoint-based methods. In this paper, a novel region duplication detection scheme is proposed based on hybrid feature and evaluative clustering. The proposed scheme is divided into two stages: the rough matching and the exact matching. In the rough matching, first, hybrid keypoints are extracted from the input image, and those keypoints are described by the unified descriptors. Second, those keypoints are matched by the g2NN strategy. Third, those matched keypoints are grouped by the proposed clustering based on evaluation. Fourth, affine transformations are estimated between these groups, and Bag of Word is used to filter inaccuracy affine transformations to improve the results of pixel level. When no affine transformation is obtained, in the exact matching, each suspicious region is handled separately. Experimental results indicate that the proposed scheme outperforms the state-of-the-art methods under various conditions.

Estimation of lighting environment for exposing image splicing forgeries

This paper proposes a novel image forensics technique to detect splicing forgeries in digital images. The method is applicable to images containing two or more persons, where the near frontal views of the faces are available. Firstly, a low-dimensional lighting model is created from a set of front pose face images of a single individual under different directional lighting environments. For this, the set of images is decomposed using principal component analysis. This low-dimensional model, which captures the lighting variation in faces, is then used to estimate the lighting environment (LE) from a given near front pose face image. In a spliced image, the LE estimated from the spliced face will be different from that estimated from the original faces. Therefore, finding the inconsistencies among the LEs estimated from different faces could reveal the splicing forgery. The experimental results on Yale Face Database B and a set of authentic and forged real-life images show the efficacy of the proposed method.

Block-based copy–move image forgery detection using DCT

Digital image forensic is a sub-area of multimedia security whose objective is to expose the malicious image manipulations in digital images. Among different types of image forgery, copy–move forgery is the most popular to forge the digital images where a part of the original digital image is copied and pasted at another position in the same image. Different methods have been developed to detect the image forgery in digital images. On the basis of our literature review, we identify that less attention is given to clustering algorithms to speed up the block matching strategy during image forgery detection process. Therefore, to address this issue, we present a pixel-based copy–move image forgery detection method to check the genuineness of digital images. Proposed method includes the following steps: (1) convert the color image into gray-scale image, (2) divide the gray-scale image into overlapping blocks of size 8 × 8, (3) feature extraction using DCT on the basis of different feature sets, (4) block clustering using K-means algorithm, and (5) radix sort for feature matching. Experimental results demonstrate that proposed method can efficiently detect the forged part from digital images.

Using machine learning and the first digit law to detect forgeries in digital images

Digital image tampering is becoming popular and it might cause serious problems in different areas. Therefore, detection forgeries in digital images are an urgent need. There are various forgery types, which can be exposed by different forensic techniques. In this paper, we propose a new detection scheme using the first-digit law (also known as Benford's law) in order to identify several types of image forgeries. We extract specific features, which are fed to a machine learning based classifier in order to distinguish between original images and manipulated images. Through experiments, we found that the proposed scheme works well for detecting double JPEG compression and Gaussian noise addition. Copy-move is among the most popular types of image forgeries, where a part of an image is copied and pasted to another position of the same image. However, we show this manipulation does not affect the law. Experiments on a large-scale image dataset show that the proposed scheme is reliable and it can achieve detection rate up to 90% or higher.

Using machine learning and the first digit law to detect forgeries in digital images

Digital image tampering is becoming popular and it might cause serious problems in different areas. Therefore, detection forgeries in digital images are an urgent need. There are various forgery types, which can be exposed by different forensic techniques. In this paper, we propose a new detection scheme using the first-digit law (also known as Benford's law) in order to identify several types of image forgeries. We extract specific features, which are fed to a machine learning based classifier in order to distinguish between original images and manipulated images. Through experiments, we found that the proposed scheme works well for detecting double JPEG compression and Gaussian noise addition. Copy-move is among the most popular types of image forgeries, where a part of an image is copied and pasted to another position of the same image. However, we show this manipulation does not affect the law. Experiments on a large-scale image dataset show that the proposed scheme is reliable and it can achieve detection rate up to 90% or higher.

Enhanced Fiilltterr-based SIFT Apprroach fforr Copy-Move Forrgerry Dettecttiion

Image forgeries are applied to give the digital images othermeanings or to deceive the viewers. Image forgeries appear inmany cases such as judges in courts, cybercrimes, military andintelligence deception, or defamation of important characters.There are many different types of image forgeries such as copymove forgery, image retouching, image splicing, image morphing,and image resampling. Copy move forgery is the widest type andeasy to apply between all digital image forgeries. Scale InvariantFeatures Transform (SIFT) algorithm is used strongly to detectcopy move forgeries due to its efficiency in digital image analysis.SIFT algorithm is extracting image features, which are invariant togeometrical transformations such as scaling, translation, androtation. These features are used in performing the matchingbetween different views of a scene or an object. This paperenhances the efficiency of using SIFT algorithm in detecting copymove forgery by two ways. Firstly, it enhances the image itself byapplying different types of digital filters to reinforce the imagefeatures giving the ability to detect forgeries. Butterworth low-passfilter, a high-pass filter, and the combination of them are appliedto this task. Secondly, the matching strategy is adapted based ona new thresholding approach to increase the true positive rateand decrease the false positive rate. Experimental results showthat the proposed approach gives better results compared withtraditional copy-move detection approaches. In addition, it gives better stability and reliability to different copy-move forgery conditions.

Application of local invariant symmetry features to detect and localize image copy move forgeries

Today whatever is seen in digital images could be unrealistic due to the advent of sophisticated systems and image editing software's. It is easy to edit digital images without leaving the traces of manipulation, therefore tampering is hard to discern visually. Among the types of digital image forgeries, realizing the copy move forgery is very challenging. Hence, this paper proposes a novel scheme to detect copy-move forgery by means of symmetry based local features. The proposed scheme can also detect the multiple copy move forgeries and localize the detected regions. The experiments are carried out by using the various datasets, and comparative study also made with the existing methods.

LBP and GLCM Based Image Forgery Recognition

The forgery of digital images became very easy and it’s very difficult to ascertain the authenticity of such images by naked eye. Among the various kinds of image forgeries, image splicing is a frequent and widely used technique. Even though various methods are available to detect image splicing forgery, authors have attempted to provide a novel hybrid method which can yield greater accuracy, sensitivity and specificity. In this method, gray level co-occurrence matrix (GLCM) features are extracted using local binary pattern (LBP) operator on the image and the detection of the splicing forged images among the authentic images is done using the popular pattern recognition algorithms such as combined k-NN (Comb-KNN), back propagation neural network (BPNN) and support vector machine (SVM). The recorded results are also compared with the existing results of the previous studies to ascertain the quality of the results.

Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients

Digital image forgery has significantly increased due to the rapid development of several tools of image manipulation. Based on the manipulation used to produce a tampered image, image forgery techniques can be characterized into three types: copy–move forgery, image splicing, and image retouching. Image splicing is achieved by adding regions from one image into another. This technique changes the content of the target image and causes variations in image features which are used to detect the forgery regions. In this study, an image splicing forgery detection method based on low-dimensional singular value decomposition of discrete cosine transform (DCT) coefficients has been presented. The suspicious input image is divided into multi-size blocks, and each block is transformed into 2D DCT. The DCT coefficients are calculated correspondingly to each block. The features from DCT are extracted using SVD algorithm. The roughness measure is calculated for the set of singular values obtained. Lastly, four types of statistical features—mean, variance, third-order moment skewness, and fourth-order moment kurtosis—are extracted from SVD features and are then arranged in a feature vector. Feature reduction has been applied by kernel principal component analysis. Finally, support vector machine is used to distinguish between the authenticated and spliced images. The proposed method was evaluated against three standard image datasets CASIA v1, DVMM v1, and DVMM v2. The proposed method shows an average detection accuracy of 97.15, 99.30, and 96.97 for DVMM v1, CASIA v1, and DVMM v2, respectively. These results outperform several current image splicing detection methods.

Blind Detection of Partial-Color-Manipulation Based on Self-PRNU Estimation

This article describes how to detect color manipulation which is a commonly used method in the field of digital image forgery. The difficulty that hue forgery does not change the image edges, shapes and gradations brings certain challenge to authenticity detection. Current methods utilize the PRNU from multiple un-tampered images, requiring the camera type to be known. However, the increasing varieties of digital devices greatly complicates the preparation of prior knowledge. This article proposes a blind detection method for partial color manipulation based on self-PRNU of suspicious image, eliminating the necessity of acquiring camera information. The authors estimate the PRNU of suspicious image by removing the regions due to its texture complexity. The tamper region is detected by calculating the correlation between estimated PRNU and residual noise. As to partial manipulation detection, an introduced threshold of connected components is used to reduce the false positive. The experimental results show that the method can effectively detect and locate the partial color manipulation.

2-Levels of clustering strategy to detect and locate copy-move forgery in digital images

Understanding is considered a key purpose of image forensic science in order to find out if a digital image is authenticated or not. It can be a sensitive task in case images are used as necessary proof as an impact judgment. it’s known that There are several different manipulating attacks but, this copy move is considered as one of the most common and immediate one, in which a region is copied twice in order to give different information about the same scene, which can be considered as an issue of information integrity. The detection of this kind of manipulating has been recently handled using methods based on SIFT. SIFT characteristics are represented in the detection of image features and determining matched points. A clustering is a key step which always following SIFT matching in-order to classify similar matched points to clusters. The ability of the image forensic tool is represented in the assessment of the conversion that is applied between the two duplicated images of one region and located them correctly. Detecting copy-move forgery is not a new approach but using a new clustering approach which has been purposed by using the 2-level clustering strategy based on spatial and transformation domains and any previous information about the investigated image or the number of clusters need to be created is not necessary. Results from different data have been set, proving that the proposed method is able to individuate the altered areas, with high reliability and dealing with multiple cloning.

Adaptive Histogram Equalization Based Image Forensics Using Statistics of DC DCT Coefficients

The vulnerability of digital images is growing towards manipulation. This motivated an area of research to deal with digital image forgeries. The certifying origin and content of digital images is an open problem in the multimedia world. One of the ways to find the truth of images is finding the presence of any type of contrast enhancement. In this work, novel and simple machine learning tool is proposed to detect the presence of histogram equalization using statistical parameters of DC Discrete Cosine Transform (DCT) coefficients. The statistical parameters of the Gaussian Mixture Model (GMM) fitted to DC DCT coefficients are used as features for classifying original and histogram equalized images. An SVM classifier has been developed to classify original and histogram equalized image which can detect histogram equalized image with accuracy greater than 95% when false rate is less than 5%.

A robust technique for copy-move forgery detection and localization in digital images via stationary wavelet and discrete cosine transform

In this era, due to the widespread availability of digital devices, various open source and commercially available image editing tools have made authenticity of image contents questionable. Copy-move forgery (CMF) is a common technique to produce tampered images by concealing undesirable objects or replicating desirable objects in the same image. Therefore, means are required to authenticate image contents and identify the tampered areas. In this paper, a robust technique for CMF detection and localization in digital images is proposed. The technique extracts stationary wavelet transform (SWT) based features for exposing the forgeries in digital images. SWT is adopted because of its impressive localization properties, in both spectral and spatial domains. More specifically approximation subband of the stationary wavelet transform is utilized as this subband holds most of the information that is best suited for forgery detection. The dimension of the feature vectors is reduced by applying discrete cosine transform (DCT). To evaluate the proposed technique, we use two standard datasets namely, the CoMoFoD and the UCID for experimentations. The experimental results reveal that the proposed technique outperforms the existing techniques in terms of true and false detection rate. Consequently, the proposed forgery detection technique can be applied to detect the tampered areas and the benefits can be obtained in image forensic applications.

Uncovering copy–move traces using principal component analysis, discrete cosine transform and Gabor filter

Digital image authenticity is always an imperative question to tackle whenever a digital image is being assessed for its content. Using digital forensic algorithms, the image will be evaluated for various traces left from numerous categories of manipulations including, among others, copy–move operations. Later this is considered an essential block in most digital image forgeries. It results in changing the information incorporated in a scene, hiding information from an image, or emphasizing some parts of the image. In this paper we propose and investigate two main approaches that differ in the feature extraction process in order to detect copy–move traces. In the first method, we use two-dimensional discrete cosine transform. Whereas in the second method, the phase response of Gabor filter is being used. Instead of being applied on the image directly, the two methods are applied over the first, the second or the third principal component of the image after being divided into overlapping blocks. Combining these conditions results in six basic implementations that are investigated under three parameters that must be optimized: block dimension, contrast and similarity thresholds. Results from testing and validation process demonstrate that the highest performance, in terms of false accept rate, is obtained when using Gabor filter associated with the first principal component of the image outperforming a reference method we implemented as well.

Color Channel Characteristics (CCC) for Efficient Digital Image Forensics

Digital image forgery has become extremely easy as low-cost image processing programs are readily available. Digital image forensics is a science of classifying images as authentic or manipulated. This paper aims at implementing a novel digital image forensics technique by exploiting an image’s Color Channel Characteristics (CCC). The CCCs considered are the noise and edge characteristics of the image. Averaging, median, Gaussian and Wiener filters along with Sobel, Canny, Prewitt and Laplacian of Gaussian (LoG) edge detectors are applied to get the noise and texture features. A complete, no reference, blind classifier for image tamper detection has been proposed and implemented. The proposed CCC classifier can detect copy-move as well as image splicing accurately with lower dimensionality. Support Vector Machine is used for classification of images as authentic or tampered. Experimental results have shown that the proposed technique outperforms the existing ones and may serve as a complete tool for digital image forensics.

Recent Advances in Passive Digital Image Security Forensics: A Brief Review

Abstract With the development of sophisticated image editing and manipulation tools, the originality and authenticity of a digital image is usually hard to determine visually. In order to detect digital image forgeries, various kinds of digital image forensics techniques have been proposed in the last decade. Compared with active forensics approaches that require embedding additional information, passive forensics approaches are more popular due to their wider application scenario, and have attracted increasing academic and industrial research interests. Generally speaking, passive digital image forensics detects image forgeries based on the fact that there are certain intrinsic patterns in the original image left during image acquisition or storage, or specific patterns in image forgeries left during the image storage or editing. By analyzing the above patterns, the originality of an image can be authenticated. In this paper, a brief review on passive digital image forensic methods is presented in order to provide a comprehensive introduction on recent advances in this rapidly developing research area. These forensics approaches are divided into three categories based on the various kinds of traces they can be used to track—that is, traces left in image acquisition, traces left in image storage, and traces left in image editing. For each category, the forensics scenario, the underlying rationale, and state-of-the-art methodologies are elaborated. Moreover, the major limitations of the current image forensics approaches are discussed in order to point out some possible research directions or focuses in these areas.