基于量化噪声的JPEG图像篡改检测

JPEG图像篡改引入的双重压缩会导致篡改区域的原始压缩特性发生改变,因此可以利用篡改区域压缩特性的不一致性来检测图像的篡改。利用该原理,提出了一种基于量化噪声的JPEG图像篡改检测算法。算法对待检测图像进行分块,计算每块的量化噪声,求取图像块的量化噪声服从均匀分布和高斯分布的概率,从而检测出篡改过的双重压缩区域。实验结果表明：该算法能有效检测双重压缩的JPEG图像篡改,并能定位出篡改区域。     

视频帧内运动目标移除篡改检测算法

针对数字视频帧内对象被移除的篡改操作,提出了一种基于主成分分析（PCA）的篡改检测算法。首先对待测视频帧与基准帧相减得到的差异帧使用稀疏表示方法进行去噪,降低噪声对随后特征提取的干扰;其次将去噪后的视频帧进行非重叠分块,利用主成分分析提取像素点的特征并构造特征向量空间;然后使用k-means算法对特征向量空间进行分类,并将分类结果用二值矩阵表示;最后对二值矩阵进行图像形态学操作得到最终检测结果。实验结果表明所提算法的检测性能指标精确度达到91%、准确度达到100%、F1值达到95.3%,比基于压缩感知的视频篡改检测算法在性能指标上有一定程度的提高。实验证明,对于背景静止的视频,该算法能够检测出帧内运动目标被删除的篡改操作,而且对有损压缩视频具有很好的鲁棒性。     

图像矩阵上的广义最大噪声分离算法

主成分分析（PCA）是模式识别中一种重要的变换工具,在图像处理的特征提取和降维方面有广泛的应用。然而,由于二维图像数据需要进行向量化处理,导致高维向量的产生和像素空间位置丢失。广义主成分分析（GPCA）则是基于图像矩阵的主成分分析推广算法,它不改变像素间的空间位置关系,而且计算量也显著降低。但主成分分析和广义主成分分析都没有考虑到实际图像中存在的噪声干扰。最大噪声分离（MNF）则是一种面向噪声干扰的变换方法,与主成分分析基于方差的最大化不同,最大噪声分离是基于信噪比的最大化。与GPCA的推广类似,在图像二维矩阵上推广最大噪声分离方法,提出一种广义最大噪声分离（GMNF）算法。该变换方法在保证重构时信噪比最大的同时,也具有不改变像素空间位置、计算量小的优点。在人脸和红外图像上的仿真实验结果验证了所提算法的有效性。     

基于核主成分分析的图像模糊篡改检测算法

现有的图像模糊篡改检测算法通常提取模糊操作引入的某单一特征进行判断,为更好地提高算法检测效率,提出基于核主成分分析的模糊篡改检测算法.通过奇异值分解提取第一组特征,计算图像二次模糊相关性作为第二组特征,计算图像质量因子作为第三组特征.运用核主成分分析方法实现多特征融合.采用支持向量机进行判断,从而实现模糊篡改检测.实验表明:该算法能够有效地检测数字篡改图像的模糊操作痕迹,并能对模糊篡改区域进行准确定位.     

基于灰度共生矩的图像区域复制篡改检测

针对图像区域复制—粘贴篡改,提出了一种基于灰度共生矩阵的检测算法。首先将待检测图像分成大小相同的多个重叠块,用灰度共生矩阵的统计量表示每块图像的纹理特征,得到图像的特征矢量。然后将特征矢量进行字典排序,并结合图像块的位移矢量,检测且定位出篡改区域。实验结果表明,该算法在抗旋转处理和效率方面均优于经典的基于主成分分析法（PCA）的检测算法。     

数字图像拷贝-移动篡改检测方法的分析

详细分析了现有的基于字典排序的图像拷贝-移动篡改检测方法,特别指出了块特征向量的排列顺序对于篡改检测效果的影响.说明了用于图像篡改检测时图像小块特征向量应满足的必要条件,指出特征向量的描述"粒度"应遵循"从粗到细"的原则且沿字典排序的先后顺序排列,并指出主成分分析变换增加了计算复杂度,降低了算法的稳健性,并不适用于基于字典排序的篡改检测方法.仿真实验结果表明了分析得到的结论.     

基于背景噪声的图像盲篡改检测

数字图像在成像过程中会产生特定的背景噪声,如果两幅不同噪声的图像拼接在一起,篡改区域和其他区的噪声会有差异。提出一种基于偏度统计特性的背景噪声估计算法,其通过对图像分块计算每块的噪声标准差,从而检测出噪声异常部分以达到篡改检测的目的。算法利用DCT变换去除原图细节部分,利用偏度统计特性估计噪声,利用条件最小值法求出噪声的标准差。算法改进了迭代求条件最小值法,利用微分方法求取最小值,避免了初始值设定问题,提高了算法的准确率。实验结果表明,提出的噪声估计算法正确率高,且对拼接篡改图像篡改检测有明显效果。     

基于多尺度主成分分析的图像局部方向估计算法

现有的大多数图像方向估计算法都对噪声非常敏感。因此,提出了一种基于主成分分析（PCA）和多尺度梯度金字塔分解的图像局部方向估计算法,其中主成分分析用于找到局部方向的最大似然（ML）估计。所提出的算法对于噪声图像非常鲁棒。在实验中,通过对模拟图像的和真实图像的方向估计,该算法都可以得到较好的估计效果,对噪声的鲁棒性较强,并且计算速度非常快。     

基于PCA和希伯特包络分析的盲隐写分析算法

为克服传统算法采用离散小波变换（Discrete Wavelet Transform,DWT）最终引起的加性噪声隐写图像检测正确率较低而虚惊率较高的问题,提出了一种新的盲隐写分析算法。综合应用主成分分析（Principal Component Analysis,PCA）和希伯特包络分析的优点,提取隐写图像高频子带希伯特包络解析信息号的主成分特征统计量,计算主成分信息熵,构建信息熵敏感特征向量。采用非线性支持向量机（Support Vector Machine,SVM）分类器,基于Matlab7.1平台进行仿真研究,结果表明：该算法对于空域和DWT域隐写检测具有较高的检测正确率和较低的虚惊率。     

基于噪声一致性的数字语音异源拼接篡改检测算法

异源拼接是一种常见的数字语音篡改行为,其主要借助音频编辑软件将不同场景中录制的语音片段拼接在一起,以达到改变语音语义的目的。考虑到不同场景中所包含的背景噪声特性往往存在差异,提出了一种基于噪声一致性的数字语音异源拼接篡改检测算法。首先,采用时间递归平均（TRA）算法提取待检测语音中所含噪声;然后,通过突变点检测（CPD）算法检测噪声方差是否存在突变来判定待检测语音是否经过篡改,并对篡改位置作出定位。实验仿真结果表明,所提算法能对数字语音中的异源篡改位置进行有效检测。     

使用背景噪声盲估计的图像真伪鉴别

数字图像获取过程中会在整幅图中产生一致的噪声,而由不同图像拼接而成的图像往往会在噪声的统计特性上不一致。本文利用这一特点,提出了一种基于背景噪声分析的图像真伪被动鉴别算法。该算法利用了图像数据的高阶统计特性对背景噪声进行盲估计,并通过相邻重叠分块间的特征估计来判断图像哪些部分被篡改。实验结果表明,该方法对于鉴别拼接而成的篡改图像有显著效果。     

基于噪声分布规律的伪造图像盲检测算法*

提出了一种基于噪声分布规律的伪造图像盲检测方法。首先利用基于边缘保护的滤波方法检测出图像中的噪声;然后计算图像中同质区域噪声的均值、方差和信噪比等统计量,通过比较图像中同质区域的噪声分布规律的相似性程度实现伪造图像鉴别。实验证明该算法能有效地检测出伪造图像。     

基于多支持区域局部亮度序的图像伪造检测

图像伪造检测是目前数字图像处理领域中的一个研究热点,其中复制-粘贴是最常用的伪造手段。由于伪造区域在粘贴前会被进行一定的尺度、旋转、JPEG压缩、添加噪声等操作,这使得检测伪造区域具有一定的挑战性。针对图像复制-粘贴伪造技术,提出一种基于多支持区域局部亮度序模式（LIOP）的图像伪造检测算法。首先,利用最大稳定极值区域（MSER）算法提取具有仿射不变性的区域作为支持区域;其次,利用非抽样Contourlet变换得到不同尺度、不同分辨率和不同方向的多个支持区域;然后,在每个支持区域上提取同时具有旋转不变性和单调亮度不变性的LIOP描述子,并利用双向距离比值法实现特征初匹配;接着,采用空间聚类将匹配的特征进行归类,进而用随机抽样一致性（RANSAC）算法对每个归类进行几何变换参数估计;最后,使用必要的后处理等操作来检测出伪造区域。实验表明,提出的算法具有较高的伪造检测精度与可信度。     

颜色解耦光响应非均匀性噪声融合凸优化的图像伪造检测算法

当前基于光响应非均匀性噪声的伪造检测算法使用了滤色器阵列,容易产生颜色插值噪声,严重影响了其噪声的提取精度及相关性检测的分辨率;且没有考虑源相机的相关性,借助局部像素统计决策进行目标识别,削弱了算法检测精度.提出了颜色解耦光响应非均匀性(,CD-PRNU color decoupled photo response non-uniformity)噪声融合凸优化方案的图像伪造检测算法.设计颜色解耦光响应非均匀性噪声;并构造了CD-PRNU噪声残留的数学计算模型;再嵌入Bayes原理,形成贝叶斯最小风险决策,利用图像全局像素,完成伪造目标检测.同时提出凸优化方案,将真伪决策演变为凸问题,降低算法复杂度.仿真结果显示:该算法能够更有效地检测出微小尺寸伪造目标,且其误检率更低.     

基于光源颜色和噪声的图像拼接篡改检测方法

数字图像拼接篡改是一种常见的图像伪造手段。在图像取证中,检测拼接伪造仍然是一项艰巨的任务。现有的拼接伪造检测方法多根据一种图像特性的不一致检测并定位篡改区域,而实际拼接篡改伪造往往会造成多种图像特性的改变。针对现有单一特征提取不能充分反映拼接图像特性导致检测精确率低的问题,提出一种通过提取光源颜色和噪声的混合特征来定位并显示拼接区域的高效图像拼接检测方法。实验结果表明,混合特征提取方法较单一特征提取方法能取得更高的检测精确率。     

Copy-Move Geometric Tampering Estimation Through Enhanced SIFT Detector Method

Digital picture forgery detection has recently become a popular and significant topic in image processing. Due to advancements in image processing and the availability of sophisticated software, picture fabrication may hide evidence and hinder the detection of such criminal cases. The practice of modifying original photographic images to generate a forged image is known as digital image forging. A section of an image is copied and pasted into another part of the same image to hide an item or duplicate particular image elements in copy-move forgery. In order to make the forgeries real and inconspicuous, geometric or post-processing techniques are frequently performed on tampered regions during the tampering process. In Copy-Move forgery detection, the high similarity between the tampered regions and the source regions has become crucial evidence. The most frequent way for detecting copy-move forgeries is to partition the images into overlapping square blocks and utilize Discrete cosine transform (DCT) components as block representations. Due to the high dimensionality of the feature space, Gaussian Radial basis function (RBF) kernel based Principal component analysis (PCA) is used to minimize the dimensionality of the feature vector representation, which improves feature matching efficiency. In this paper, we propose to use a novel enhanced Scale-invariant feature transform (SIFT) detector method called as RootSIFT, combined with the similarity measures to mark the tampered areas in the image. The proposed method outperforms existing state-of-the-art methods in terms of matching time complexity, detection reliability, and forgery location accuracy, according to the experimental results. The F1 score of the proposed method is 92.3% while the literature methods are around 90% on an average.     

基于JPEG块效应频域特性的合成图像检测

JPEG图像在压缩过程中所产生的块效应在功率谱曲线上体现为周期性波峰,而篡改JPEG图像所造成块效应不一致将导致周期性波峰的衰弱或消除。利用上述原理,提出了一种基于JPEG块效应频域特性的合成图像检测算法。算法对待测图像进行去噪,提取包含块效应的噪声,对其进行重叠分块并求得每块的块效应度量值,依据该度量值检测并定位篡改区域。实验结果表明,相对于传统的基于块效应不一致的算法,能够更好地检测多种不同图像格式的合成和篡改区域较小等情况。     

Exposing image resampling forgery by using linear parametric model

Resampling forgery generally refers to as the technique that utilizes interpolation algorithm to maliciously geometrically transform a digital image or a portion of an image. This paper investigates the problem of image resampling detection based on the linear parametric model. First, we expose the periodic artifact of one-dimensional 1-D) resampled signal. After dealing with the nuisance parameters, together with Bayes’ rule, the detector is designed based on the probability of residual noise extracted from resampled signal using linear parametric model. Subsequently, we mainly study the characteristic of a resampled image. Meanwhile, it is proposed to estimate the probability of pixels’ noise and establish a practical Likelihood Ratio Test (LRT). Comparison with the state-of-the-art tests, numerical experiments show the relevance of our proposed algorithm with detecting uncompressed/compressed resampled images.     

Detecting image forgeries using metrology

Image forgery technology has become popular for tampering with digital photography. This paper presents a framework for detecting fake regions using single view metrology and enforcing geometric constraints from shadows. In particular, we describe how to (1) estimate the region of interest’s 3D measurements from a single perspective view of a scene given only minimal geometric information determined from the image, (2) determine the fake region by exploring the imaged shadow relations that are modeled by the planar homology. We also show that image forgery on the vertical plane or arbitrary plane can be detected through the measurement on such plane. Our approach efficiently extracts geometric constraints from a single image and makes use of them for the digital forgery detection. Experimental results on both the synthetic data against noise and visually plausible images demonstrate the performance of the proposed method.     

A new keypoint-based copy-move forgery detection for small smooth regions

Copy-move forgery is one of the most common types of image forgeries, where a region from one part of an image is copied and pasted onto another part, thereby concealing the image content in the latter region. Keypoint based copy-move forgery detection approaches extract image feature points and use local visual features, rather than image blocks, to identify duplicated regions. Keypoint based approaches exhibit remarkable performance with respect to computational cost, memory requirement, and robustness. But unfortunately, they usually do not work well if smooth background areas are used to hide small objects, as image keypoints cannot be extracted effectively from those areas. It is a challenging work to design a keypoint-based method for detecting forgeries involving small smooth regions. In this paper, we propose a new keypoint-based copy-move forgery detection for small smooth regions. Firstly, the original tampered image is segmented into nonoverlapping and irregular superpixels, and the superpixels are classified into smooth, texture and strong texture based on local information entropy. Secondly, the stable image keypoints are extracted from each superpixel, including smooth, texture and strong texture ones, by utilizing the superpixel content based adaptive feature points detector. Thirdly, the local visual features, namely exponent moments magnitudes, are constructed for each image keypoint, and the best bin first and reversed generalized 2 nearest-neighbor algorithm are utilized to find rapidly the matching image keypoints. Finally, the falsely matched image keypoints are removed by customizing the random sample consensus, and the duplicated regions are localized by using zero mean normalized cross-correlation measure. Extensive experimental results show that the newly proposed scheme can achieve much better detection results for copy-move forgery images under various challenging conditions, such as geometric transforms, JPEG compression, and additive white Gaussian noise, compared with the existing state-of-the-art copy-move forgery detection methods.