一种基于优化马尔科夫特征的图像篡改盲检测算法

文中主要针对拼接图像篡改检测,提出了一种基于优化马尔科夫特征的盲检测算法.该算法在传统马尔科夫特征的基础上,研究了不同相邻BDCT系数对的关联性对于拼接图像的检测能力,进而设计了一种基于互信息量最大化的加权BDCT系数转移概率特征;同时,通过对所有BDCT系数对进行预分组,降低了算法的计算量以及最终的特征维度.最后,采用支持向量机（SVM）作为分类器,在哥伦比亚大学提供的标准图像拼接库上完成测试,取得了较高的平均检测准确率（91.2％）,优于现有的代表性方法.     

基于马尔科夫和HHT的图像拼接盲检测

基于对图像拼接技术的分析,提出了一种基于马尔科夫模型与Hilbert-Huang变换（HHT）的图像拼接盲检测算法。该算法计算图像DCT域上的马尔科夫转移概率矩阵,同时对图像进行Hilbert-Huang分析,得到两类特征值集,并通过计算相关系数矩阵分析了两者之间的相关性,最后使用支持向量机进行训练与分类。实验结果表明,相对于已有文献,该算法具有较高的检测准确率。     

一种改进的图像拼接检测算法

通过对图像拼接技术特点的分析,提出一种基于图像纹理特征分析和马尔科夫模型的改进的拼接图像检测算法。该算法计算图像DCT域上的马尔科夫转移概率矩阵,同时对图像进行纹理分析,得到两类特征共178维。为评估该检测算法的性能,提出了一个具体实现方案,提取了图片数据集的特征,使用支持向量机（Support Vector Machine,SVM）对特征数据进行训练与分类。实验表明,该方法取得了较好的分类效果。     

数字图像拼接篡改盲取证技术研究

研究图像的篡改识别问题,由于数字图像能够被轻易的篡改并且很难发现改动痕迹,对篡改像素不融合现象识别不清,导致图像篡改很难被肉眼识别。为解决上述问题,从篡改者的角度对目前流行的篡改手段做了新的分类,详细分析了各种篡改取证技术的优缺点。提出了一种基于统计特征分类的盲检测算法,实验表明,从图像的双谱幅值和相角检测可以准确识别出篡改后的图像,为篡改图像的识别提供了依据。     

一种基于差分DCT系数对直方图的图像取证方法

提出了一种基于差分DCT域系数对直方图的图像拼接篡改检测方法.该方法首先对图像进行DCT变换,而后分别计算DCT系数矩阵的水平、垂直、主对角线、副对角线四个方向的差分DCT系数矩阵,并对得到的差分DCT系数矩阵进行系数对直方图化,提取特征向量.最后,利用支持向量机对真实图像和篡改后的图像进行分类识别.实验结果表明,在相关的测试数据集上,和现存的一些算法相比,该方法不仅具有较低的计算复杂度,同时,其检测性能在目前所有提出的算法中达到最高,性能优良.     

基于马尔科夫识别的敌我目标识别新方法

针对敌我识别系统在现代战争中的保密要求,提出一种将马尔科夫系统识别技术应用于敌我识别的新方法,每个发射机按照系统分配的转移矩阵发射随机码,接收机利用已知的不同我方作战单元的转移矩阵,判断码序列所属,实现我方目标的识别。与传统方法相比,发射机每次按照一定的转移概率发射服从马尔科夫分布的随机编码,大大提高了敌方截获和破译的难度,提升了系统的抗欺骗干扰性能。仿真结果表明,该方法在发射序列比较长的情况下,可以获得准确的识别结果。     

基于扩散方程和MRF的SAR图像分割

该文提出了一种基于图像扩散方程和马尔科夫随机场(MRF)的合成孔径雷达(SAR)图像分割方法。在传统MRF算法的基础之中,引入对图像的扩散,用来平滑SAR图像中的噪声,保护图像中的边缘部分,并且加快收敛的速度。首先对输入的SAR图像进行扩散,通过MRF进行统计,得到图像中各点的后验概率,再对得到的后验概率进行扩散。与传统的MRF算法进行比较,该文的方法较好地去除了误分割斑块,减少算法的运行时间。     

基于JPEG压缩不变量和数字水印的图像认证方法

提出一种抗JPEG压缩的图像认证算法。根据图像不同块中位置相同的DCT系数之间的大小关系在JPEG压缩之后几乎没有发生变化这一性质,对图像进行分析生成特征编码,并将特征编码加密后以水印方式嵌入图像。认证时只需将待测图像的特征编码与从中抽取出的解密水印进行比较,利用篡改矩阵鉴别是否有内容被篡改,并给出具体的篡改位置。实验结果表明,该算法有很好的抗JPEG压缩性能,并可有效地检测出恶意篡改及其发生的位置。     

基于小波多尺度分析的综合特征图像检索

以整数小波变换为基础,提出了一种综合颜色和空间特征的图像检索算法.该算法首先对图像做整数小波变换,提取其低频系数矩阵中环形区域的F-范数作为颜色特征;然后对低频分量分块并编码,利用马尔可夫链特性提取一步转移概率矩阵作为空间特征;再综合利用上述两个特征计算图像间的相似度,并进行彩色图像检索.通过对不同类型图像的检索对比实验结果表明,这种图像检索方法是行之有效的.     

结合尺度空间FAST角点检测器和SURF描绘器的图像特征

为了获得能够很好地应用于远距离目标识别且计算快速的图像特征,本文提出了一种结合尺度空间FAST(加速分割试验特征)角点检测器和SURF(加速鲁棒特征)描绘器的新特征算法。SURF算法利用了基于快速海森矩阵的关键点检测算法,容易从图像中快速海森矩阵响应值较高但信息匮乏的边缘区域提取大量关键点,进而导致大量的低独特性特征以及不可忽视的误匹配率;同时,其高斯滤波带来的图像模糊使得算法在远距离目标区域内检测到的关键点数量减少,从而对远距离目标的识别造成困难。针对SURF算法的这些问题,本文方法利用尺度空间FAST算法代替快速海森矩阵,并利用具有良好的独特性的SURF描绘器。该方法能够有效地减少对上述类型的干扰性关键点的提取,对远距离目标的关键点检测的性能相对于快速海森矩阵具有显著优势,且其独特性优于同样使用FAST角点检测器的BRISK特征。实验结果表明,对于带有光照变化、尺度变化和3D视角变化目标,基于本文特征的识别算法的识别正确率高于基于SIFT、SURF和BRISK特征的识别算法;本文特征适用于远程目标识别,同时其计算速度达到了与SURF接近的水平。     

Image forgery detection algorithm based on U-shaped detection network

Aiming at the defects of traditional image tampering detection algorithm relying on single image attribute,low applicability and current high time-complexity detection algorithm based on deep learning,an U-shaped detection network image forgery detection algorithm was proposed.Firstly,the multi-stage feature information in the image by using the continuous convolution layers and the max-pooling layers was extracted by U-shaped detection network,and then the obtained feature information to the resolution of the input image through the upsampling operation was restored.At the same time,in order to ensure higher detection accuracy while extracting high-level semantic information of the image,the output features of each stage in U-shaped detection network would be merged with the corresponding output features through the upsampling layer.Further the hidden feature information between tampered and un-tampered regions in the image upon the characteristics of the general network was explored by U-shaped detection network,which could be realized quickly by using its end-to-end network structure and extracting the attributes of strong correlation information among image contexts that could ensure high-precision detection results.Finally,the conditional random field was used to optimize the output of the U-shaped detection network to obtain a more exact detection results.The experimental results show that the proposed algorithm outperforms those traditional forgery detection algorithms based on single image attribute and the current deep learning-based detection algorithm,and has good robustness.     

基于LPP和改进SIFT的copy-move篡改检测

图像的复制-粘贴篡改检测是图像篡改检测领域中的重要组成部分。本文基于SIFT算法以及LPP的降维思想,提出了一种新的篡改检测算法。本文在SIFT算法的基础上,使用LPP算法对SIFT算法生成的特征点以及特征向量进行降维。使得传统SIFT算法在实际应用中特征点数目过多、特征向量维数过高等缺陷得到了解决。并使用凝聚型层次聚类算法对相似的特征点进行聚类,完成了对图像复制-粘贴篡改区域的检测。在文章的最后,本文对哥伦比亚大学复制-粘贴图像库里的100张图片进行实验。实验结果表明,不管篡改区域后处理方式是拉伸还是旋转,本文算法都能比传统的SIFT、SURF、PCA-SIFT等算法生成更少的特征点数目和更低的特征向量维度,使得检测效率以及检测正确率得到有效提升。      

Fast copy-move forgery detection algorithm based on group SIFT

Aiming at the high computational complexity of the existing copy-move image forgery detection algorithm,a copy-move forgery detection algorithm based on group scale-invariant feature transform (SIFT) was proposed.Firstly,the simple linear iterative clustering (SLIC) was utilized to divide the input image into non-overlapping and irregular blocks.Secondly,the structure tensor was introduced to classify each block as flat blocks,edge blocks and corner blocks,and then the SIFT feature points extracted from the block were taken as the block features.Finally,the forgery was located by the inter-class matching of the block features.By means of inter-class matching and feature point matching,the time complexity of the proposed copy-move forgery detection algorithm in feature matching and locating forgery region was effectively reduced while guaranteeing the detection effect.The experimental results show that the accuracy of the proposed algorithm is 97.79%,the recall rate is 90.34%,and the F score is 93.59%,the detecting time for the image with size of 1024×768 is 12.72 s,and the detecting time for the image with size of 3000×2000 was 639.93 s.Compared with the existing copy-move algorithm,the proposed algorithm can locate the forgery region quickly and accurately,and has high robustness.     

像素预测误差耦合似然映射的图像伪造检测算法

为了解决当前图像伪造定位技术因使用了CFA 插值,易形成颜色插值噪声而降低分辨率,导致其难以检测微小篡改区域,使其伪造检测精度较低等不足,本文提出了像素预测误差耦合似然映射的图像伪造检测算法。首先,分析颜色滤波阵列CFA插值模型,并从图像中提取绿色分量;随后,嵌入权重因子,构造预测误差及其权重方差计算模型;根据预测误差与贝叶斯理论,定义伪造特征统计模型,识别出趋于零的特征值;最后,根据特征统计模型,建立其似然率模型,输出伪造映射,完成检测。仿真结果表明：与当前图像伪造定位机制相比,本文算法拥有更强的鲁棒性,能识别定位出微小伪造像素;且拥有更高的AUC值与理想的ROC曲线。     

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.     

基于级联卷积神经网络的图像篡改检测算法

基于卷积神经网络的图像篡改检测算法利用卷积神经网络的学习能力可以实现不依赖于单一图像属性的图像篡改检测,弥补传统图像篡改检测方法依赖单一图像属性、适用度不高的缺陷。利用深层多神经元的单一网络结构的图像篡改检测算法虽然可以学习更高级的语义信息,但检测定位篡改区域效果并不理想。该文提出一种基于级联卷积神经网络的图像篡改检测算法,在卷积神经网络所展示出来的普遍特性的基础上进一步探究其深层次的特性,利用浅层稀神经元的级联网络结构弥补以往深层多神经元的单一网络结构在图像篡改检测中的缺陷。该文提出的检测算法由级联卷积神经网络和自适应筛选后处理两部分组成,级联卷积神经网络实现分级式的篡改区域定位,自适应筛选后处理对级联卷积神经网络的检测结果进行优化。通过实验对比,该文算法展示了较好的检测效果,且具有较高的鲁棒性。     

Copy-move image forgery detection based on Gabor magnitude

With advancement of media editing software, even people who are not image processing experts can easily alter digital images. Various methods of digital image forgery exist, such as image splicing, copy-move forgery, and image retouching. The most common method of tampering with a digital image is copy-move forgery, in which a part of an image is duplicated and used to substitute another part of the same image at a different location. In this paper, we present an efficient and robust method to detect such artifacts. First, the tampered image is segmented into overlapping fixed-size blocks, and the Gabor filter is applied to each block. Thus, the image of Gabor magnitude represents each block. Secondly, statistical features are extracted from the histogram of orientated Gabor magnitude (HOGM) of overlapping blocks, and reduced features are generated for similarity measurement. Finally, feature vectors are sorted lexicographically, and duplicated image blocks are identified by finding similarity block pairs after suitable post-processing. To enhance the algorithm’s robustness, a few parameters are proposed for removing the wrong similar blocks. Experiment results demonstrate the ability of the proposed method to detect multiple examples of copy-move forgery and precisely locate the duplicated regions, even when dealing with images distorted by slight rotation and scaling, JPEG compression, blurring, and brightness adjustment.     

Copy-move forgery detection and localization by means of robust clustering with J-Linkage

Understanding if a digital image is authentic or not, is a key purpose of image forensics. There are several different tampering attacks but, surely, one of the most common and immediate one is copy-move. A recent and effective approach for detecting copy-move forgeries is to use local visual features such as SIFT. In this kind of methods, SIFT matching is often followed by a clustering procedure to group keypoints that are spatially close. Often, this procedure could be unsatisfactory, in particular in those cases in which the copied patch contains pixels that are spatially very distant among them, and when the pasted area is near to the original source. In such cases, a better estimation of the cloned area is necessary in order to obtain an accurate forgery localization. In this paper a novel approach is presented for copy-move forgery detection and localization based on the J-Linkage algorithm, which performs a robust clustering in the space of the geometric transformation. Experimental results, carried out on different datasets, show that the proposed method outperforms other similar state-of-the-art techniques both in terms of copy-move forgery detection reliability and of precision in the manipulated patch localization.     

指数矩耦合局部敏感哈希的图像伪造检测算法

为了解决图像伪造检测算法在定位篡改内容时忽略了不同颜色分量之间的关系,使其对图像特征描述不足,导致其识别结果中存在误检与漏检等情况,本文提出了基于多元指数矩与欧式局部敏感哈希的图像伪造检测算法。引入高斯低通滤波,消除可疑图像中的噪声;随后,将滤波图像分割为一系列的重叠圆形子块,改善其对旋转等内容操作的鲁棒性;基于四元指数矩(QEM),计算每个圆形子块的QEM,以提取相应的鲁棒特征,将其组合成特征矢量;采用欧式局部敏感哈希机制,生成每个子块对应的哈希序列;计算任意两个相邻哈希元素之间的空间距离,通过与预设阈值比较,完成所有子块的匹配;最后,借助随机样本一致性方法来剔除错误匹配,通过形态学处理,定位出篡改内容。实验数据显示：较已有的伪造检测方法而言,在各种几何内容修改下,所提算法具有更高的伪造检测准确性。     

引入图像特征的直觉模糊推理医学图像融合方法

针对现有的直觉模糊推理在医学图像中的应用展开研究,在直觉模糊推理有局限的情况下,引入图像的特征参数作为融合判断条件,提出新的图像融合算法。该算法以直觉模糊推理作为基础,加入新的判定参数再进行融合,采用新的算法进行实验仿真,结果显示新方法具有一定的改进和优势。