A robust content based image watermarking using local invariant histogram

Desynchronization attack is known as one of the most difficult attacks to resist, which can desynchronize the location of the watermark and hence causes incorrect watermark detection. Based on multi-scale SIFT (Scale Invariant Feature Transform) detector and local image histogram shape invariance, we propose a new content based image watermarking algorithm with good visual quality and reasonable resistance toward desynchronization attacks in this paper. Firstly, the stable image feature points are extracted from the original host by using multi-scale SIFT detector, and the local feature regions (LFRs) are constructed adaptively according to the feature scale theory. Then, the discrete Fourier transform (DFT) is performed on the LFR, and the local image histogram is extracted from a selected DFT amplitude range. Finally, the bins of the histogram are divided into many groups, and the digital watermark is embedded into LFR by reassigning the number of DFT amplitudes in bin groups. By binding the watermark with the geometrically invariant image features, the watermark detection can be done without synchronization error. Experimental results show that the proposed image watermarking is not only invisible and robust against common image processing operations such as sharpening, noise adding, and JPEG compression, but also robust against the desynchronization attacks such as rotation, translation, scaling, row or column removal, and cropping.     

基于SIFT的椭圆区域鲁棒数字水印方案

如何有效抵抗去同步攻击是数字图像水印研究领域的热点问题之一。利用图像仿射协变特征,提出一种可有效抵抗去同步攻击的鲁棒水印算法。对目前流行的利用多尺度Harris和SIFT描述算子来匹配图像的方法,后者有较好的匹配效果,对恢复同步水印更加稳定,并且能较好抵抗去同步攻击。该算法利用性能稳定的SIFT算子提取图像特征点,并通过基于最小生成树聚类算法的选择策略获得一组稳定且彼此独立的椭圆仿射协变特征区域,基于特征区域,利用椭圆归一化得到具有缩放和旋转不变性的圆形区域。将圆形区域进行非下采样轮廓变换（NSCT）,其中非下采样轮廓变换不仅克服了小波（Wavelet）变换的非奇异性最优基缺点,而且提供了优于轮廓（Contourlet）变换的平移不变性。将水印嵌入变换后的低频子带中。该算法实现盲提取,仿真实验结果表明,提出的算法是有效的且对常规图像处理、几何攻击以及组合攻击均具有较好的鲁棒性。     

基于LFRs的大容量抗几何攻击水印算法*

如何有效抵抗几何攻击是目前水印技术研究的难点之一,且已有抗几何攻击水印算法的嵌入容量有限。提出了一种利用尺度不变特征变换（SIFT）特征点确定的局部特征区域（LFRs）嵌入水印的大容量抗几何攻击的水印算法。算法首先从图像的非抽样的Contourlet域（NSCT）低频分量中提取出SIFT中等尺度的稳定特征点,并通过最小生成树聚类算法的选择策略获得一组分布均匀且彼此独立的圆形特征区域;然后对每个圆形区域进行等角度的扇形分割和等面积的同心圆环分割,划分成等面积的子块;最后采用奇偶量化将经过混沌加密的水印嵌入到     

基于第二代Bandelet变换的抗几何攻击图像水印

抗几何攻击的鲁棒图像水印设计是目前水印技术研究的难点和热点之一. 文中分析了图像的Bandelet变换特性, 提出了一种以图像特征点矢量集为特征向量的回归支持向量机(Support vector regression, SVR)和第二代 Bandelet变换的抗几何攻击图像水印算法,采取的主要方法包括: 1)在Bandelet变换提取的刻画图像局部特征的几何流系数上, 采用奇偶量化嵌入水印; 2)利用Harris-Laplace算子从归一化的含水印图像中提取具有几何形变鲁棒性的图像特征点,构造特征点矢量集 作为特征向量,应用回归支持向量机对几何变换参数进行训练学习; 3)水印检测时, 先利用SVR训练模型得到待检测图像所受几何攻击的参数并作几何校正,然后通过奇偶检测器盲提取水印.仿真实验表明,所提出的水印算 法不仅具有良好的透明性,而且对常规图像处理、一般性几何攻击和组合攻击均具有良好的鲁棒性.     

基于改进SIFT的抗几何攻击的数字水印

通过改进的SIFT（尺度不变特征变换）算法提出了一种可有效抵抗几何攻击的鲁棒数字水印算法。此算法利用改进的SIFT进行水印信号的同步;水印嵌入采用圆环的嵌入模式,在空域以奇偶量化形式嵌入;通过奇偶检测器提取水印。实验结果表明,改进的SIFT大大降低特征点匹配的维数,提高匹配速率,同时该算法能获得很好的图像质量,能有效抵抗几何攻击和常规的信号处理攻击。     

基于改进SIFT特征和图转换匹配的图像匹配算法

针对SIFT特征在纹理丰富的图像中提取较多的伪点和不稳定的点而影响图像匹配的问题, 提出了一种基于Harris阈值准则的局部不变特征图像匹配算法。该算法在提取SIFT不变特征的基础上, 利用Harris阈值准则对所提取到的不变特征进行选择, 剔除了图像区域中大量可区分性较差的特征点, 从而得到了相对稳定和可区分性较好的特征点。其次, 结合不变特征矢量与图转换匹配(GTM)的方法对提取到的稳定特征点进行了精确匹配。实验对比结果表明, 用取得稳定的特征点, 进而结合一种好的匹配策略, 能够更加增强图像匹配的高效性和鲁棒性。     

融合HU不变矩和SIFT特征的商标检索

利用商标图像的形状特征,提出了一种融合图像全局特征和局部特征的商标检索算法。其中全局特征反应了图像的整体信息,这些信息可用来较快地建立候选图像库,而局部特征则可以更准确地与候选图像进行匹配。提取图像的HU不变矩进行初步检索,按相似度排序,在此结果集的基础上对候选图像通过提取SIFT特征进行精确匹配。实验结果表明,该方法既保持了SIFT特征的良好描述能力,又减少了精确匹配需要的计算次数,降低了复杂度。     

构建近邻上下文的拷贝图像检索

目的 以词袋模型为基础的拷贝图像检索方法是当前最有效的方法。然而,由于局部特征量化存在信息损失,导致视觉词汇区别能力不足和视觉词汇误匹配增加,从而影响了拷贝图像检索效果。针对视觉词汇的误匹配问题,提出一种基于近邻上下文的拷贝图像检索方法。该方法通过局部特征的上下文关系消除视觉词汇歧义,提高视觉词汇的区分度,进而提高拷贝图像的检索效果。方法 首先,以距离和尺度关系选择图像中某局部特征点周围的特征点作为该特征点的上下文,选取的上下文中的局部特征点称为近邻特征点;再以近邻特征点的信息以及与该局部特征的关系为该局部特征构建上下文描述子;然后,通过计算上下文描述子的相似性对局部特征匹配对进行验证;最后,以正确匹配特征点的个数衡量图像间的相似性,并以此相似性选取若干候选图像作为返回结果。结果 在Copydays图像库进行实验,与Baseline方法进行比较。在干扰图像规模为100 k时,相对于Baseline方法,mAP提高了63%。当干扰图像规模从100 k增加到1 M时,Baseline的mAP值下降9%,而本文方法下降3%。结论 本文拷贝图像检索方法对图像编辑操作,如旋转、图像叠加、尺度变换以及裁剪有较高的鲁棒性。该方法可以有效地应用到图像防伪、图像去重等领域。     

基于SIFT特征的人耳识别

人耳的角度变化和遮挡是人耳识别中的难点问题,SIFT局部描述算子具有对图像尺度缩放、平移、旋转等的不变性,因此提出利用SIFT特征的人耳识别算法。该算法将人耳图像划分为相互重叠的网格区域,在每个子区域中计算SIFT的局部特征,再计算测试图像与训练图像的匹配相关度作为图像的全局特征,将SIFT的局部和全局特征相结合作为人耳识别的标准。通过在人耳库中的实验表明,此算法优于传统的全局方法,对于人耳角度变化和遮挡具有较好的鲁棒性,并且适用于单训练样本的情况。     

基于尺度不变特征变换的快速图像拷贝检测

针对传统基于尺度不变特征变换（SIFT）特征的图像拷贝检测算法特征提取速度慢、匹配效率不高的问题,提出了一种基于SIFT特征点位置分布与方向分布特征的快速图像拷贝检测算法。首先,提取SIFT特征点二维位置信息,通过计算各个特征点与图像中心点的距离、角度,分块统计各区间的特征点数量,依据数量关系量化生成二值哈希序列,构成一级鲁棒特征;然后,根据特征点一维方向分布特征分块统计各方向子区间特征点数量,依据数量关系构成二级图像特征;最后,拷贝检测时采用级联式过滤框架作出是否为拷贝的判断。仿真实验结果表明,与传统SIFT以128维特征描述子为基础构建哈希序列的图像拷贝检测算法相比,所提算法在保证鲁棒性与独特性不降低的同时,特征提取时间缩短为原来的1/20,匹配时间也缩短了1/2以上,可满足在线拷贝检测的需求。     

融合傅里叶描述子和尺度不变特征转换特征的商标检索

针对传统商标检索算法中全局特征容易造成误检,而局部特征SIFT对轮廓描述能力不强及算法复杂度高的问题,提出了一种融合图像全局特征和局部特征的商标检索算法。其中全局特征反应了图像的整体信息,这些信息可用来较快地建立候选图像库,而局部特征则可以更准确地与候选图像进行匹配。首先提取图像的傅里叶描述子进行初步检索,并按相似度排序,然后在此结果集的基础上对候选图像通过提取SIFT特征进行精确匹配。实验结果表明,该方法既保持了SIFT特征较高的查全率和查准率,优于傅里叶描述子单一特征,而且检索速度比SIFT单一特征显著提高,能很好地应用于商标图像检索系统中。     

Invariant image watermarking using multi-scale Harris detector and wavelet moments

Desynchronization attack is known as one of the most difficult attacks to resist, which can desynchronize the location of the watermark and hence causes incorrect watermark detection. It is a challenging work to design a robust image watermarking scheme against desynchronization attacks. Based on multi-scale Harris detector and wavelet moment theory, we propose a new content based image watermarking algorithm with low computational complexity, good visual quality and reasonable resistance toward desynchronization attacks in this paper. Firstly, the steady image feature points are extracted from the origin host by using multi-scale Harris detector, and the local feature regions (LFRs) are constructed adaptively according to the feature scale theory. Then, the LFRs are image normalized, and significant regions are obtained from the normalized LFRs by utilizing the invariant centroid theory. Finally, the digital watermark is embedded into the LFRs by modifying wavelet moment invariants of the significant regions. By binding the watermark with the geometrically invariant image features, the watermark detection can be done without synchronization error. Experimental results show that the proposed image watermarking is not only invisible and robust against common image processing operations as sharpening, noise adding, and JPEG compression etc, but also robust against the desynchronization attacks such as rotation, translation, scaling, row or column removal, cropping, and local random bend etc.     

A robust color image watermarking using local invariant significant bitplane histogram

Desynchronization attacks that cause displacement between embedding and detection are usually difficult for watermark to survive. It is a challenging work to design a robust image watermarking scheme against desynchronization attacks, especially for color images. In this paper, we propose a robust color image watermarking approach based on local invariant significant bitplane histogram. The novelty of the proposed approach includes: 1) A fast and effective color image feature points detector is constructed, in which probability density and color invariance model are used; 2) The fully affine invariant local feature regions are built based on probability density Hessian matrix; and 3) The invariant significant bitplane histograms are introduced to embed digital watermark. The extensive experimental works are carried out on a color image set collected from Internet, and the preliminary results show that the proposed watermarking approach can survive numerous kinds of distortions, including common image processing operations and desynchronization attacks.     

A feature-based robust digital image watermarking against geometric attacks

Based on scale space theory and an image normalization technique, a new feature-based image watermarking scheme robust to general geometric attacks is proposed in this paper. First, the Harris–Laplace detector is utilized to extract steady feature points from the host image; then, the local feature regions (LFR) are ascertained adaptively according to the characteristic scale theory, and they are normalized by an image normalization technique; finally, according to the predistortion compensation theory, several copies of the digital watermark are embedded into the nonoverlapped normalized LFR by comparing the DFT mid-frequency magnitudes. Experimental results show that the proposed scheme is not only invisible and robust against common signals processing methods such as median filtering, sharpening, noise adding, and JPEG compression etc., but also robust against the general geometric attacks such as rotation, translation, scaling, row or column removal, shearing, local geometric distortion and combination attacks etc.     

Accurate and robust localization of duplicated region in copy–move image forgery

Copy–move image forgery detection has recently become a very active research topic in blind image forensics. In copy–move image forgery, a region from some image location is copied and pasted to a different location of the same image. Typically, post-processing is applied to better hide the forgery. Using keypoint-based features, such as SIFT features, for detecting copy–move image forgeries has produced promising results. The main idea is detecting duplicated regions in an image by exploiting the similarity between keypoint-based features in these regions. In this paper, we have adopted keypoint-based features for copy–move image forgery detection; however, our emphasis is on accurate and robust localization of duplicated regions. In this context, we are interested in estimating the transformation (e.g., affine) between the copied and pasted regions more accurately as well as extracting these regions as robustly by reducing the number of false positives and negatives. To address these issues, we propose using a more powerful set of keypoint-based features, called MIFT, which shares the properties of SIFT features but also are invariant to mirror reflection transformations. Moreover, we propose refining the affine transformation using an iterative scheme which improves the estimation of the affine transformation parameters by incrementally finding additional keypoint matches. To reduce false positives and negatives when extracting the copied and pasted regions, we propose using “dense” MIFT features, instead of standard pixel correlation, along with hysteresis thresholding and morphological operations. The proposed approach has been evaluated and compared with competitive approaches through a comprehensive set of experiments using a large dataset of real images (i.e., CASIA v2.0). Our results indicate that our method can detect duplicated regions in copy–move image forgery with higher accuracy, especially when the size of the duplicated region is small.     

基于图像特征和三角剖分的水印算法

针对特征点发生偏差、水印检测效率降低的问题,提出一种将水印嵌入与特征点分开的算法。通过Harris特征点构造凸多边形区域,利用动态规划算法三角剖分凸多边形,水印信息嵌入在每个三角形的质心周围,少数且稳定的Harris特征点用来匹配原始图像与测试图像,估计计算几何变换参数,从而对测试图像进行校正。实验结果表明,该方法能改善水印对RST攻击的鲁棒性。     

Robust image watermarking technique using triangular regions and Zernike moments for quantization based embedding

Watermarking is a tool to embed information in the image to provide authentication, copyrights protection, copy control, etc. Some watermarking techniques are robust to intentional /unintentional attacks on the watermarked image. In this study, we propose a robust watermarking approach that can resist geometrical attacks. The proposed technique exploits both the robust image feature points and local Zernike moments for embedding the information. Delaunay tessellation is employed to divide image into distinct triangular segments based on robust features. These features are identified using Harris detector. Zernike moments are calculated for each selected triangular segment, and then the watermark is embedded in the magnitude of Zernike moments using dither modulation. It can be observed from the experimental results that by using proposed approach, the watermark can be detected even in the presence of geometrical distortion, i.e. rotation, cropping, and scaling, and JPEG compression attack.

     

一种新型遥感图像配准方法

提出了一种新型全自动稳健的遥感图像配准算法。首先,在图像二维平面空间和尺度空间中同时检测局部极值作为特征点,并在特征点邻域提取局部不变特征描述子一尺度不变特征变换（SIFT）。然后,利用距离测度进行SIFT特征匹配得到初步的匹配集合。最后,运用稳健的随机采样一致性（RANSAC）算法将匹配点集划分为内点和外点,在内点域上精确地估计出图像变换模型。实验利用仿真数据测试了SIFT特征的可重复性和可匹配性,利用卫星图像验证了该自动配准算法的有效性和稳健性。     

基于图像特征点的强鲁棒数字水印嵌入方案

提出了一种抵抗一般性几何攻击的数字水印新算法. 该算法首先利用多尺度 Harris 检测算子从载体图像中提取出稳定的特征点; 然后根据特征尺度自适应确定局部特征区域, 并对其实施归一化处理; 最后结合预失真补偿理论, 采纳 DFT 中频幅值比较策略将水印信息重复嵌入到多个归一化局部特征区域内. 仿真实验表明, 本文算法不仅具有较好的透明性, 而且对常规信号处理和一般性几何攻击均具有较好的鲁棒性.