采用量化离散余弦变换系数检测视频单帧连续多次复制粘贴篡改

目前大多数时域视频帧复制粘贴篡改检测算法都是针对至少20帧以上的视频子序列的复制粘贴篡改,而对单帧复制粘贴篡改无法判断。而根据人眼视觉感知的特性,修改视频内容需要至少15帧以上的帧操作,因此篡改帧想通过单帧复制粘贴篡改来达到想要的效果,必须进行连续多次粘贴操作。为了检测这种篡改方式,针对性地提出了一种基于量化离散余弦变换(DCT)系数的视频单帧连续多次复制-粘贴篡改检测算法。首先,将视频转换为图像,采用量化后的DCT系数作为视频帧图像特征向量,并通过计算巴氏(Bhattacharyya)系数来衡量两相邻帧帧间相似度;再设定阈值来判断两相邻帧帧间相似度是否有异常,最后根据出现相似度异常的帧是否连续,以及连续出现的帧数来判断视频是否经过篡改,并定位篡改位置。实验结果表明,所提算法对不同场景的视频都能检测,不仅检测速度快,而且不受再压缩因素影响,算法的正确率高、漏检率低。     

基于JPEG双量化效应的图像盲取证

JPEG图像的双量化效应为JPEG图像的篡改检测提供了重要线索.根据JPEG图像被局部篡改后,又被保存为JPEG格式时,未被篡改的区域(背景区域)的离散余弦变换(DCT)系数会经历双重JPEG压缩,篡改区域的DCT系数则只经历了1次JPEG压缩.而JPEG图像在经过离散余弦变换后其DCT域的交流(AC)系数的分布符合一个用合适的参数来描述的拉普拉斯分布,在此基础上提出了一种JPEG图像重压缩概率模型来描述重压缩前后DCT系数统计特性的变化,并依据贝叶斯准则,利用后验概率表示出图像篡改中存在的双重压缩效应块和只经历单次压缩块的特征值.然后设定阈值,通过阈值进行分类判断就可以实现对篡改区域的自动检测和提取.实验结果表明,该方法能快速并准确地实现篡改区域的自动检测和提取,并且在第2次压缩因子小于第1次压缩因子时,检测结果相对于利用JPEG块效应不一致的图像篡改盲检测算法和利用JPEG图像量化表的图像篡改盲检测算法有了明显的提高.     

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。     

基于JPEG的固定背景视频压缩算法研究

为了对固定背景视频进行压缩并获得较高的压缩比,在JPEG静止图像压缩标准的基础上提出了一种新的应用于固定背景视频压缩的算法.对第一帧图像进行JPEG格式的压缩并保存量化后的离散余弦变换系数,对第一帧后的每一帧图像,在进行离散余弦变换和量化后,先同存储器内的第一帧图像的离散余弦变换系数进行异或运算再进行熵编码.通过使用该算法和H.264视频压缩标准对同一段固定背景视频进行压缩并比较压缩后的数据量,表明了该算法具有较高的压缩比.     

Forensics for partially double compressed doctored JPEG images

Digital image forensics is required to investigate unethical use of doctored images by recovering the historic information of an image. Most of the cameras compress the image using JPEG standard. When this image is decompressed and recompressed with different quantization matrix, it becomes double compressed. Although in certain cases, e.g. after a cropping attack, the image can be recompressed with the same quantization matrix too. This JPEG double compression becomes an integral part of forgery creation. The detection and analysis of double compression in an image help the investigator to find the authenticity of an image. In this paper, a two-stage technique is proposed to estimate the first quantization matrix or steps from the partial double compressed JPEG images. In the first stage of the proposed approach, the detection of the double compressed region through JPEG ghost technique is extended to the automatic isolation of the doubly compressed part from an image. The second stage analyzes the doubly compressed part to estimate the first quantization matrix or steps. In the latter stage, an optimized filtering scheme is also proposed to cope with the effects of the error. The results of proposed scheme are evaluated by considering partial double compressed images based on the two different datasets. The partial double compressed datasets have not been considered in the previous state-of-the-art approaches. The first stage of the proposed scheme provides an average percentage accuracy of 95.45%. The second stage provides an error less than 1.5% for the first 10 DCT coefficients, hence, outperforming the existing techniques. The experimental results consider the partial double compressed images in which the recompression is done with different quantization matrix.     

Video text detection and localization in intra-frames of H.264/AVC compressed video

Video texts are closely related to the video content. The video text information can facilitate content based video analysis, indexing and retrieval. Video sequences are usually compressed before storage and transmission. A basic step of text-based applications is text detection and localization. In this paper, an overlaid text detection and localization method is proposed for H.264/AVC compressed videos by using the integer discrete cosine transform (DCT) coefficients of intra-frames. The main contributions of this paper are in the following two aspects: 1) coarse text blocks detection using block sizes and quantization parameters adaptive thresholds; 2) text line localization according to the characteristics of text in intra frames of H.264/AVC compressed domain. Comparisons are made with the pixel domain based text detection method for the H.264/AVC compressed video. Text detection results on five H.264/AVC video sequences under various qualities show the effectiveness of the proposed method.     

<Emphasis Type="Bold">Inter-frame forgery detection in H.264 videos using motion and brightness gradients</Emphasis>

In the midst of low cost and easy-to-use multimedia editing software, which make it exceedingly simple to tamper with digital content, the domain of digital multimedia forensics has attained considerable significance. This research domain deals with production of tools and techniques that enable authentication of digital evidence prior to its use in various critical and consequential matters, such as politics, criminal investigations, defense planning. This paper presents a forensic scheme for detection of frame-based tampering in digital videos, especially those captured by surveillance cameras. Frame-based tampering, which involves insertion, removal or duplication of frames into or from video sequences, is usually very difficult to detect via simple visual inspection. Such forgeries, however, disturb the temporal correlation among successive frames of the tampered video. These disturbances, when analyzed in an appropriate manner, help reveal the evidence of forgery. The forensic technique presented in this paper relies on objective analysis of prediction residual and optical flow gradients for the detection of frame-based tampering in MPEG-2 and H.264 encoded videos. The proposed technique is also capable of determining the exact location of the forgery in the given video sequence. Results of extensive experimentation in diverse and realistic forensic set-ups show that the proposed technique can detect and locate tampering with an average accuracy of 83% and 80% respectively, regardless of the number of frames inserted, removed or duplicated.     

基于DCT域的数字图像双水印算法

提出了一种基于DCT域的数字图像双水印算法,将鲁棒水印与脆弱水印同时嵌入到DCT的中低频系数中,鲁棒水印和脆弱水印的嵌入与顺序无关,且不相互影响.首先,对DCT变换后的系数按照它们的位置进行了特殊的分类,通过分类后每一类中正负号的数量来表达鲁棒水印信息,增强了算法的鲁棒性.对相同的DCT 系数使用邻近值比较法嵌入脆弱水印.实验结果表明鲁棒水印可以实现了对图像载体的版权认证,脆弱水印实现了对图像载体的完整性保护和篡改定位.     

双重认证的变换域图像半脆弱数字水印算法

提出了一种DCT域与DWT域相结合的双重认证图像半脆弱数字水印算法,定义了一个小波系数量化函数以实现水印的嵌入与提取,根据图像局部特性,该量化函数可动态地进行调整;同时设计了三个混沌密钥,结合DCT域定义水印及其嵌入位置．实验表明,该算法在保持对常见的JPEG压缩稳健的同时,能有效地区分偶然失真与恶意篡改。     

Fast scene change detection using direct feature extraction fromMPEG compressed videos

In order to process video data efficiently, a video segmentation technique through scene change detection must be required. This is a fundamental operation used in many digital video applications such as digital libraries, video on demand (VOD), etc. Many of these advanced video applications require manipulations of compressed video signals. So, the scene change detection process is achieved by analyzing the video directly in the compressed domain, thereby avoiding the overhead of decompressing video into individual frames in the pixel domain. In this paper, we propose a fast scene change detection algorithm using direct feature extraction from MPEG compressed videos, and evaluate this technique using sample video data, First, we derive binary edge maps from the AC coefficients in blocks which were discrete cosine transformed. Second, we measure edge orientation, strength and offset using correlation between the AC coefficients in the derived binary edge maps. Finally, we match two consecutive frames using these two features (edge orientation and strength). This process was made possible by a new mathematical formulation for deriving the edge information directly from the discrete cosine transform (DCT) coefficients. We have shown that the proposed algorithm is faster or more accurate than the previously known scene change detection algorithms     

基于频域水印的人脸图像窜改检测认证方法

以DeepFake为代表的AI换脸技术为人们的生活带来诸多负面影响,现有的人脸窜改检测算法鲁棒性较弱,缺乏可解释性。针对这一问题提出一种离散小波变换（DWT）、离散余弦变换（DCT）、奇异值分解（SVD）相结合的人脸频域水印算法（face frequency-domain watermarking,Face-FW）,通过提取图像人脸特征并压缩加密生成二值水印嵌入图像频域以达到检测人脸窜改、认证原人脸归属人的目的,同时提出动态特征融合算法以降低Face-FW适用范围。选取人脸图像标准数据集CASIA-FaceV5和IMDB-WIKI部分图像嵌入水印并窜改人脸生成测试集CASIA-DF和IMDB-DF。实验结果表明,Face-FW在两个测试集上分别有97.6%和96.9%的检测窜改成功率,优于对比方法,并且算法能够根据非特征融合水印提供人脸认证,具有较强的鲁棒性和可解释性。     

No-reference image quality assessment based on localized discrete cosine transform for JPEG compressed images

In this paper, we propose a new no-reference image quality assessment for JPEG compressed images. In contrast to the most existing approaches, the proposed method considers the compression processes for assessing the blocking effects in the JPEG compressed images. These images have blocking artifacts in high compression ratio. The quantization of the discrete cosine transform (DCT) coefficients is the main issue in JPEG algorithm to trade-off between image quality and compression ratio. When the compression ratio increases, DCT coefficients will be further decreased via quantization. The coarse quantization causes blocking effect in the compressed image. We propose to use the DCT coefficient values to score image quality in terms of blocking artifacts. An image may have uniform and non-uniform blocks, which are respectively associated with the low and high frequency information. Once an image is compressed using JPEG, inherent non-uniform blocks may become uniform due to quantization, whilst inherent uniform blocks stay uniform. In the proposed method for assessing the quality of an image, firstly, inherent non-uniform blocks are distinguished from inherent uniform blocks by using the sharpness map. If the DCT coefficients of the inherent non-uniform blocks are not significant, it indicates that the original block was quantized. Hence, the DCT coefficients of the inherent non-uniform blocks are used to assess the image quality. Experimental results on various image databases represent that the proposed blockiness metric is well correlated with the subjective metric and outperforms the existing metrics.

     

H.264中基于DCT域的视频可控加密研究

提出一种适用于H．264／AVC的DCT系数分层可控加扰算法,按照特定规律修改Intra帧的DCT系数,再利用帧间预测将加扰效果扩散至所有帧。最终实现视频的无级扰乱。实验结果表明,此算法克服以往空间加扰算法造成压缩效率下降的不足,具有很好的加扰效果,适用于H．264／AVC的视频系统中。     

Double JPEG compression detection based on block statistics

In this paper, a novel method is proposed to detect the aligned double JPEG compression with different quantization matrix. The proposed method is based on the theory that the correlation among adjacent coefficients of frequency spectrum in DCT blocks is enhanced after DCT transformation, and the correlation among same locations in adjacent DCT blocks is strong. Classification features are divided into two types, the intra-block frequency domain features and the inter-block frequency domain features. The intra-block frequency domain features are used to catch the strong correlation among adjacent coefficients in DCT blocks, and the inter-block frequency domain features are used to catch the correlation among same locations of adjacent DCT blocks. Then the intra-block frequency domain features with inter-block frequency domain features are combined as the classification features. Finally, the classification features are used to train classifiers to detect double JPEG compression. The results of extensive experiments demonstrate the effectiveness of the proposed method.     

基于多级时空域3D卷积的换脸视频检测方法

近年来,视频换脸技术发展迅速。该技术可被用于伪造视频来影响政治行动和获得不当利益,从而给社会带来严重危害,目前已经引起了各国政府和舆论的广泛关注。本文通过分析现有的主流视频换脸生成技术和检测技术,指出当前主流的生成方法在时域和空域中均具有伪造痕迹和生成损失。而当前基于神经网络检测合成人脸视频的算法大部分方法只考虑了空域的单幅图像特征,并且在实际检测中有明显的过拟合问题。针对目前检测方法的不足,本文提出一种高效的基于时空域结合的检测算法。该方法同时对视频换脸生成结果在空域与时域中的伪造痕迹进行捕捉,其中,针对单帧的空域特征设计了全卷积网络模块,该模块采用3D卷积结构,能够精确地提取视频帧阵列中每帧的伪造痕迹;针对帧阵列的时域特征设计了卷积长短时记忆网络模块,该模块能够检测伪造视频帧之间的时序伪造痕迹;最后,根据特征分类设计特征网络金字塔网络结构,该结构能够融合不同尺寸的时空域特征,通过多尺度融合来提高分类效果,并减少过拟合现象。与现有方法相比,该方法在训练中的收敛效果和分类效果方面有明显优势。除此之外,我们在保证检测准确率的前提下采用较少的参数,相比现有结构而言训练效率更高。     

A novel forensic image analysis tool for discovering double JPEG compression clues

This paper presents a novel technique to discover double JPEG compression traces. Existing detectors only operate in a scenario that the image under investigation is explicitly available in JPEG format. Consequently, if quantization information of JPEG files is unknown, their performance dramatically degrades. Our method addresses both forensic scenarios which results in a fresh perceptual detection pipeline. We suggest a dimensionality reduction algorithm to visualize behaviors of a big database including various single and double compressed images. Based on intuitions of visualization, three bottom-up, top-down and combined top-down/bottom-up learning strategies are proposed. Our tool discriminates single compressed images from double counterparts, estimates the first quantization in double compression, and localizes tampered regions in a forgery examination. Extensive experiments on three databases demonstrate results are robust among different quality levels. F ₁-measure improvement to the best state-of-the-art approach reaches up to 26.32 %. An implementation of algorithms is available upon request to fellows.     

基于压缩域水印的AVS视频认证*

为了提高压缩域视频水印的安全性,提出一种基于压缩域的AVS视频认证水印新算法。它从视频空间的三维特性出发,利用I帧分块能量关系、GOP结构信息、帧结构信息等构造特征码。在嵌入算法上,将特征码同时嵌入到中频DCT系数和运动矢量中,在认证端将重建特征值和提取的双水印进行比较。仿真实验结果表明,该算法具有较好的窜改认证能力。     

基于DWT和DCT的自适应双重音频水印

针对数字音频版权保护和内容认证的问题, 提出了一种用于版权保护和内容认证的自适应双重音频水印算法。算法对每段原始音频信号进行离散小波变换和离散余弦变换, 分别提取混合变换域的低频系数和中低频系数作为水印的构造和嵌入域, 利用音频载体的统计特性自适应地构造零水印和嵌入半脆弱水印, 实现音频版权保护和内容认证。实验结果表明, 该算法的不可感知性很好, 在抵抗多种攻击时具有良好的鲁棒性, 并且能够对恶意窜改进行定位。     

奇偶量化DCT系数实现文本信息隐藏

提出了一种基于图像载体的文本信息隐藏算法。引入一种新的基于地址错位的随机发生器算法,对所嵌入信息进行置乱。根据置乱后信息按照特定规则对图像量化系数进行奇偶处理,从而实现文本信息嵌入。针对图像压缩时所导致的误码,利用JND模型,提出了一种新的基于提取对比的误码修正算法。实验表明,该算法具有较强的鲁棒性和不可见性,在抵抗JPEG压缩、噪声、剪切等干扰具有较优良的性能。