A forgery detection algorithm for exemplar-based inpainting images using multi-region relation

The identification of image authenticity has received much attention because of the increasing power of image editing methods. This paper proposes a novel forgery detection algorithm to recognize tampered inpainting images, which is one of the effective approaches for image manipulation. The proposed algorithm contains two major processes: suspicious region detection and forged region identification. Suspicious region detection searches the similarity blocks in an image to find the suspicious regions and uses a similarity vector field to remove the false positives caused by uniform area. Forged region identification applies a new method, multi-region relation (MRR), to identify the forged regions from the suspicious regions. The proposed approach can effectively recognize if an image is a forged one and identify the forged regions, even for the images containing the uniform background. Moreover, we propose a two-stage searching algorithm based on weight transformation to speed up the computation speed. The experimental results show that the proposed approach has good performance with fast speed under different kinds of inpainting images.     

基于超像素形状特征的图像复制粘贴篡改检测算法

针对传统图像复制粘贴篡改检测方法中划分子块的数目过大导致算法时间复杂度过高且抵抗几何变换能力较弱的问题,提出一种基于超像素形状特征的图像复制粘贴篡改检测算法.首先提出基于小波对比度自适应划分超像素的方法分割图像并提取稳定的特征点;然后提出新颖的形状编码方式提取超像素形状特征,并与特征点融合,估计可疑伪造区域;最后对可疑伪造区域进行二次超像素分割和匹配,精确定位篡改区域.实验结果表明,提出的算法具有抵抗几何变换、噪声、模糊和JPEG压缩的能力.     

特征匹配结合自适应阈值的图像伪造检测

针对现有图像复制移动伪造检测方法对图像中存在同质纹理或均匀区域检测困难、相关参数阈值选择影响检测等问题,提出一种基于特征匹配与自适应阈值的图像复制移动伪造检测方法。首先通过定义和优化成本函数来制定交互作用机制,包括匹配和变换估计步骤;然后在迭代过程中执行步骤,使相关阈值的选择和估计更合理,自动识别和定位伪造区域;最后采用检测系统的相互作用关系,检测并修正步骤中发生的错误。实验结果表明:相比传统的复制移动伪造检测方法,在对伪造图像的像素图像精度水平、旋转和缩放的鲁棒性、检测专业伪造图像以及变换矩阵的精度等不同情况,所提方法效率更高。     

一种基于自适应闭值的图像伪造检测算法

图像伪造检测是数字取证领域一个发展迅速的研究方向。复制一移动是最常见的图像伪造方式之一,其目的是通过隐藏或克隆对象来创建新的图像内容场景。复制一移动伪造检测的主要依据是图像中存在较大面积的相同或非常相似的区域对。针对以往检测方法对图像中存在同质纹理或均匀区域检测困难以及相关参数阂值选择不确定等现状,提出一种基于自适应阂值的图像复制一移动伪造检测算法,该算法不但使相关阂值的选择和估计更合理,而且能够自动识别和定位伪造区域。通过在包含同质或均匀区域的彩色伪造图像中的实验,进一步验证了本算法的有效性。     

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.     

检测小篡改区域的U型网络

目的 图像篡改区域检测是图像取证领域的一个挑战性任务,其目的是找出图像的篡改区域。传统方法仅针对某种特定的篡改方式进行设计,难以检测其他篡改方式的图像。基于卷积神经网络的方法能够自适应地提取特征,同时检测包含多种篡改方式的图像。但是其中多数方法都选择增强图像的噪声特征,这种机制无法较好处理篡改区域与原图像来源相同、噪声相似的情况。多数方法还忽略了篡改区域过小而产生的样本不平衡问题,导致检测效果不佳。方法 提出了一个基于区域损失的用于检测小篡改区域的U型网络,该网络构建了一个异常区域特征增强机制,放大与图像背景差异较大的异常区域的特征。此外,还利用区域损失增强对篡改区域框内像素的判别能力,可以解决因篡改区域过小而产生的样本不平衡问题。结果 消融实验说明了异常区域特征增强机制和区域损失机制的有效性;对JPEG压缩和高斯模糊的对抗性测试证明了模型的鲁棒性;在CASIA2.0（CASI-A image tampering detection evaluation database）、NIST2016（NIST nimble 2016 datasets）、COLUMBIA （Columbia uncompressed image splicing detection evaluation dataset）和COVERAGE （a novel database forcopy-move forgery detection）数据集上与最新方法进行比较时,本文方法取得了最优性能,其F1 score分别为0.979 5、0.982 2、0.995 3和0.987 0。结论 本文的异常区域特征增强机制和区域损失机制能有效提高模型性能,同时缓解篡改区域过小导致的样本不平衡问题,大量实验也表明了本文提出的小篡改区域检测方法的优越性。     

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.     

Geometric transformations parameters estimation from copy-move forgery using image blobs and keypoints

A copy-move forgery is a passive tampering wherein one or more regions have been copied and pasted within the same image. Often, geometric transformations, including scale, rotation, and rotation+scale are applied to the forged areas to conceal the counterfeits to the copy-move forgery detection methods. Recently, copy-move forgery detection using image blobs have been used to tackle the limitation of the existing detection methods. However, the main limitation of blobs-based copy-move forgery detection methods is the inability to perform the geometric transformation estimation. To tackle the above-mentioned limitation, this article presents a technique that detects copy-move forgery and estimates the geometric transformation parameters between the authentic region and its duplicate using image blobs and scale-rotation invariant keypoints. The proposed algorithm involves the following steps: image blobs are found in the image being analyzed; scale-rotation invariant features are extracted; the keypoints that are located within the same blob are identified; feature matching is performed between keypoints that are located within different blobs to find similar features; finally, the blobs with matched keypoints are post-processed and a 2D affine transformations is computed to estimate the geometric transformation parameters. Our technique is flexible and can easily take in various scale-rotation invariant keypoints including AKAZE, ORB, BRISK, SURF, and SIFT to enhance the effectiveness. The proposed algorithm is implemented and evaluated on images forged with copy-move regions combined with geometric transformation from standard datasets. The experimental results indicate that the new algorithm is effective for geometric transformation parameters estimation.

     

基于DWT和形态学滤波的图像伪造检测方法

针对图像中复制-移动和拼接形式的图像伪造检测,提出一种基于离散小波变换(DWT)和形态学滤波的图像伪造检测方法。首先,将图像转换为灰度图,通过应用DWT获得LH、HL和HH子带。然后,通过阈值判断来获得伪造图像区域的边缘,并通过形态学滤波来连接边缘使其清晰化。最后,提取伪造区域的SIFT特征,并通过相似性检测来寻找图像中与伪造区域相似的区域,以此来确定伪造类型。实验结果表明,该方法能够准确检测出伪造区域和伪造类型。     

基于均值漂移的图像复制粘贴伪造盲检测

摘要：随着数字多媒体技术及计算机网络技术的发展,数字图像在信息技术时代扮演着越来越重要的角色,图像的真实性成为现代人们广泛关注的热点之一,为此提出了一种基于均值漂移的图像复制粘贴伪造盲检测算法。提取图像的SURF（Speed up robust feature）特征点,通过最近邻匹配方法进行特征匹配,滤除冗余点,初步定位复制粘贴伪造区域。均值漂移（Mean Shift）将具有相同或相似属性的图像像素分割为同一区域,利用匹配后的SURF特征点与其所在均值漂移分割区域的位置依赖关系确定伪造区域,并采用边缘直方图和HSV颜色直方图衡量特征点所在分割区域与相邻分割区域间的相似度,进一步细化伪造检测结果,最终实现图像的复制粘贴伪造盲检测。实验结果表明,该算法能够鲁棒地、高效地检测出图像的复制粘贴伪造区域。     

利用小波域同态滤波的伪造图像检测方法

针对伪造图像中常用的模糊操作,提出一种伪造图像的检测方法,该方法首先对伪造图像进行小波域同态滤波,增强处于高频段的人为模糊边缘,然后利用数学形态方法腐蚀掉自然边缘,保留增强的模糊边缘,最后对腐蚀后的边缘图像进行区域标定,从而定位出伪造区域。实验证明该算法相对基于传统同态滤波伪造检测方法,能够较准确定位伪造区域,降低误检率。     

Image forgery detection using steerable pyramid transform and local binary pattern

In this paper, a novel image forgery detection method is proposed based on the steerable pyramid transform (SPT) and local binary pattern (LBP). First, given a color image, we transform it in the YCbCr color space and apply the SPT transform on chrominance channels Cb and Cr, yielding a number of multi-scale and multi-oriented subbands. Then, we describe the texture in each SPT subband using LBP histograms. The histograms from each subband are concatenated to produce a feature vector. Finally, a support vector machine uses the feature vector to classify images into forged or authentic. The proposed method has been evaluated on three publicly available image databases. Our experimental results demonstrate the effectiveness of the proposed method and its superiority over some recent other methods.     

基于Tamura纹理特征的Copy-Move图像篡改盲检测

针对图像盲认证中一种常见的Copy-Move型图像篡改,提出了基于图像的Tamura纹理特征的Copy-Move型篡改区域的检测和定位算法。该算法提取每一图像块的Tamura纹理特征组成图像的特征向量,用字典排序法对特征向量进行排序,利用欧式距离计算图像块的相似性,以检测和定位被篡改的图像区域。实验结果表明,该算法能有效地检测和定位被篡改的图像区域。     

预训练驱动的多模态边界感知视觉Transformer

卷积神经网络(convolutional neural network, CNN)在图像篡改检测任务中不断取得性能突破,但在面向真实场景下篡改手段未知的情况时,现有方法仍然无法有效地捕获输入图像的长远依赖关系以缓解识别偏差问题,从而影响检测精度.此外,由于标注困难,图像篡改检测任务通常缺乏精准的像素级图像标注信息.针对以上问题,提出一种预训练驱动的多模态边界感知视觉Transformer.首先,为捕获在RGB域中不可见的细微伪造痕迹,引入图像的频域模态并将其与RGB空间域结合作为多模态嵌入形式.其次利用ImageNet对主干网络的编码器进行训练以缓解当前训练样本不足的问题.然后, Transformer模块被整合到该编码器的尾部,以达到同时捕获低级空间细节信息和全局上下文的目的,从而提升模型的整体表征能力.最后,为有效地缓解因伪造区域边界模糊导致的定位难问题,构建边界感知模块,其可以通过Scharr卷积层获得的噪声分布以更多地关注噪声信息而不是语义内容,并利用边界残差块锐化边界信息,从而提升模型的边界分割性能.大量实验结果表明,所提方法在识别精度上优于现有的图像篡改检测方法,并对不同的...     

Image copy-move forgery passive detection based on improved PCNN and self-selected sub-images

Image forgery detection remains a challenging problem. For the most common copy-move forgery detection, the robustness and accuracy of existing methods can still be further improved. To the best of our knowledge, we are the first to propose an image copy-move forgery passive detection method by combining the improved pulse coupled neural network (PCNN) and the self-selected sub-images. Our method has the following steps: First, contour detection is performed on the input color image, and bounding boxes are drawn to frame the contours to form suspected forgery sub-images. Second, by improving PCNN to perform feature extraction of sub-images, the feature invariance of rotation, scaling, noise adding, and so on can be achieved. Finally, the dual feature matching is used to match the features and locate the forgery regions. What's more, the self-selected sub-images can quickly obtain suspected forgery sub-images and lessen the workload of feature extraction, and the improved PCNN can extract image features with high robustness. Through experiments on the standard image forgery datasets CoMoFoD and CASIA, it is effectively verified that the robustness score and accuracy of proposed method are much higher than the current best method, which is a more efficient image copy-move forgery passive detection method.     

基于区域划分和四元数的彩色图像复制粘贴篡改检测

现有的篡改检测方法中特征点提取不充分会导致篡改检测精度不高,特征点描述符识别率差,针对该问题提出一种基于颜色矩的区域划分和四元数Hu矩的彩色图像复制粘贴篡改检测算法。首先,使用自适应形态重建算法对图像进行超像素分割,通过密度聚类算法对图像自适应划分区域;其次,提出一种关键点提取方法得到均匀的SIFT特征点;然后,在一种新颖的彩色图像四元数表示方法中构建局部高斯金字塔提取Hu矩特征;最后,利用2NN进行特征匹配后,结合Delaunay三角形算法定位出复制粘贴篡改区域。在公共数据集上的实验结果表明,该算法可以更有效地定位篡改区域。     

基于公共因子提取的数字图像篡改检测

针对数字篡改图像的背景区域和篡改区域都经过模糊的情况,提出了1种基于公共因子提取的模糊篡改检测算法。将图像的线性空间滤波转换成按照行和列方向的一维卷积,通过判断提取出公共因子系数之间的方差来进行篡改检测。该方法特别适用于轻微模糊的情况并且可以同时检测图像的copy_move型篡改。实验说明了该方法对数字图像被动认证的有效性。     

融合全局时序和局部空间特征的伪造人脸视频检测方法

近年来,深度学习在人工智能领域表现出优异的性能。基于深度学习的人脸生成和操纵技术已经能够合成逼真的伪造人脸视频,也被称作深度伪造,让人眼难辨真假。然而,这些伪造人脸视频可能会给社会带来巨大的潜在威胁,比如被用来制作政治虚假新闻,从而引发政治暴力或干扰正常选举等。因此,亟需研发对应的检测方法来主动发现伪造人脸视频。现有的方法在制作伪造人脸视频时,容易在空间上和时序上留下一些细微的伪造痕迹,比如纹理和颜色上的扭曲或脸部的闪烁等。主流的检测方法同样采用深度学习,可以被划分为两类,即基于视频帧的方法和基于视频片段的方法。前者采用卷积神经网络（Convolutional Neural Network,CNN）发现单个视频帧中的空间伪造痕迹,后者则结合循环神经网络（Recurrent Neural Network,RNN）捕捉视频帧之间的时序伪造痕迹。这些方法都是基于图像的全局信息进行决策,然而伪造痕迹一般存在于五官的局部区域。因而本文提出了一个统一的伪造人脸视频检测框架,利用全局时序特征和局部空间特征发现伪造人脸视频。该框架由图像特征提取模块、全局时序特征分类模块和局部空间特征分类模块组成。在FaceForensics++数据集上的实验结果表明,本文所提出的方法比之前的方法具有更好的检测效果。     

基于自适应提点鲁棒定位的图像复制粘贴篡改检测

复制-粘贴篡改检测(Copy-Move Forgery Detection, CMFD)是数字图像篡改的一种常见方式, 近年来已成为多媒体取证领域一个重要的研究方向. 本文提出一种鲁棒的复制-粘贴篡改检测算法, 基于构造波动函数自适应获取阈值的方法均匀提取图像特征点, 可在篡改区域小或平滑的情况下进行鲁棒检测. 引入DBQ-LSH匹配算法进行特征匹配, 降低了时间复杂度. 提出基于不变矩LBP图像的定位方法, 在图像受到噪声攻击和JPEG压缩攻击下能精准定位篡改位置. 实验结果表明, 该算法具有优良的检测正确率(图像级)和检测精度 (像素级).     

基于模糊不变矩的复制粘贴伪造检测方法

随着各种高级图像处理算法以及相应图像处理软硬件的出现,即使非专业人士也很容易篡改图像,并使人肉眼很难甚至无法识别。针对一种常见的图像篡改--复制粘贴伪造,提出了一个能自动检测并标识数字图像中复制区域的方法。将图像分成多个重叠块,每块的特征用由模糊不变矩计算得到的模糊不变量表示,按照预定的相似标准来确定图像篡改区域。实验结果表明：相对于基于PCA的方法,该方法在抗模糊处理方面具有明显的优势。