基于离散四元数余弦变换的彩色图像数字水印技术

将离散四元数余弦变换(DQCT)应用于彩色图像的数字水印技术中,提出了一种在彩色图像中嵌入水印的新技术。应用四元数理论把彩色图像作为一整体进行余弦变换,在彩色宿主图像的DQCT域中实现彩色水印图像的嵌入。实验表明,该方法具有较好的抗压缩能力,对高斯噪声、椒盐噪声和缩放攻击具有较好的鲁棒性。     

基于四元数主成分分析的人脸识别算法

本文把四元数矩阵运算引入主成分分析,提出了一种应用于彩色图像的四元数主成分分析人脸识别算法。该算法首先用四元数矩阵模型表示彩色人脸图像,然后求该四元数矩阵的协方差矩阵,及其特征向量,通过将彩色人脸图像投影到四元数协方差矩阵特征向量组成的特征空间,比较其与已知人脸在特征空间的位置,从而达到识别彩色人脸的目的。实验表明,采用该算法能得到比经典的特征脸法更高的识别率。     

基于四元数矩阵奇异值的目标特征提取与识别

在弹道中段,目标的微动差异是识别弹头和诱饵的有效特征.但目标微动特征参数的提取往往受到目标平动补偿精度、雷达装备工作状态和环境等因素的限制,进而导致目标识别率降低.首先建立了基于四元数的弹头与诱饵微动模型,将目标的微多普勒时频像视为彩色图像,并将彩色图像用四元数矩阵模型描述.根据奇异值向量的稳定性和旋转不变性,提出了基于四元数矩阵奇异值分解和支持向量机的弹道目标微多普勒特征提取与分类识别方法.仿真结果表明:四元数矩阵奇异值构成的特征向量比基于Hu矩的特征向量更加有效;提高信噪比,有助于提高分类器的目标识别率;目标径向速度估计误差的增大,会降低分类器的目标识别率;增大雷达的脉冲重复频率可以明显提高目标的正确识别率.     

四元数域彩色图像整体式水印算法

该文提出一种结合四元数变换域和四元数分解方法的整体式彩色图像水印算法。首先对彩色载体图像进行分块四元数傅里叶变换得到其频域矩阵,然后对频域单位小块进行四元数奇异值分解,根据分解得到四元数酉矩阵前若干列中对角线元素的幅值构造水印序列,并将水印隐藏到分解得到的实系数奇异值中。仿真实验表明,该文提出的水印方法不仅可以把嵌入水印带来的误差扩散到载体图像的各个颜色分量上,而且比传统的将彩色图像划分为各个单独色彩通道,分别进行水印嵌入的方法不可见性更好,并且,通过构造与奇异值酉矩阵相关的水印序列可以有效解决现有四元数水印算法存在的误检测率以及水印图像易伪造问题。     

客观评估彩色图像质量的超复数奇异值分解法

本文利用超复数直接对彩色图像建模,保存了彩色图像完整的信息;基于超复数奇异值分解(也称四元数奇异值分解QSVD)提出一种全新的图形化与数值化相结合的彩色图像质量评估测度,不仅能判断图像失真等级,还能判断不同的失真类型.测试结果表明,本文提出的算法比传统的MSE、PSNR以及MSSIM等算法性能更优.     

彩色图像分割算法研究

图像分割是图像分析和模式识别所要解决的基本问题和难点问题。彩色图像提供了比灰度图像更多的信息,灰度图像处理思路在某些场合已不能满足人们的需要,本文除了系统阐述常用彩色图像分割算法外还提出了一种基于四元数的分割算法。     

基于分数阶四元数傅里叶变换的彩色图像自适应水印算法

针对现有一些彩色图像自适应水印算法在自适应过程中未充分考虑色彩信息或者在嵌入过程中未考虑彩色载体图像分量的整体性等不足,该文提出一种基于分数阶四元数傅里叶变换(FrQFT)的彩色图像自适应数字水印算法。首先利用人类视觉系统(HVS)提取彩色载体图像块的纹理、边缘和色调掩蔽特性,并依据这些特性对适合嵌入图像块自适应分配嵌入强度,然后在FrQFT域以自适应强度采用量化索引调制算法和冗余嵌入策略嵌入水印。实验结果表明,该算法优于现有的基于四元数傅里叶变换(QFT)的算法以及基于分数阶傅里叶变换(FrFT)的算法,具有较好的不可见性和鲁棒性。     

客观评价彩色图像质量的全四元数结构相似度方法

在不损失彩色图像颜色信息的基础上,通过定义一 种全四元数模型 将四元数的3个虚部以及实部全部用于表示彩色图像的结构信息,从而在完整保留颜色信息 的基础上提高了四元数矩阵的信息承载量。为了进一步增加与主观感知的一致性,将彩色图 像的细节信息和颜色分量合并作为四元数的实部和虚部,进而改进传统的图像质 量评价结构相似度(SSIM)方法,采用四元数结构相似度方法 实现了对待测图像的质量评价。实验结 果表明,本文方法既保留了彩色图像的颜色信息,又增强了图像内容中人眼 敏感的细节信息,采用LIVE数据库和IVC数据库验证了本文方法的评价指标,实验结果 表明, 所提指标与人眼主观感知的一致程度要好于传统的图像质量评价方法以及纯四元数SSIM方法。在交叉失真实验中,量化评价结果的Kendall等级相关系数 (KRCC),Spearman等级相关系 数(SRCC)以及均方根误差(RMSE)为0.6929、0.881以及 7.506,均好于实验中采用的其它几种方法。     

基于四元数的彩色图像边缘检测研究

为了实现彩色图像边缘检测,建立了彩色图像自动边缘检测算法。对彩色图像基于四元数的表示方法进行描述,针对基于snake算子实现彩色图像边缘检测算法进行了研究。首先,根据彩色图像三原色的基本特征,利用四元数的矢量表示方法以及四元数基本运算方法进行描述;其次,介绍了snake算子的基本原理,检测过程等。最后,构造了双四元数和snake算子的彩色图像边缘检测算法。实验结果表明,利用文中算法获得的彩色图像边缘检测保留了原图像的自身信息,边缘信息完整。该算法基本满足彩色图像边缘检测的稳定可靠、信息完整、抗干扰能力强等要求。     

基于QDCT和贝叶斯谱熵的盲彩色图像质量评价

图像质量评价算法在评价彩色图像质量时,往往 会因损失色彩信息或者破坏彩色图像结构的整体性, 而使得评价结果与人眼观测结果不一致。由于图像越模糊其频谱的高频分量分布越不均匀, 基于四元数离 散余弦变换(QDCT)和贝叶斯谱熵,提出了一种无参考模糊彩色图像质量评价算法。首先,利 用四元数矩阵 对彩色图像进行表示并分解成不重叠的8×8 pixel的子矩阵。其次 ,对每一个子矩阵进行QDCT后得到子 矩阵的频谱。最后,通过贝叶斯谱熵衡量频谱中高频分量分布的均匀性,实现彩色图像质量 评价。所提算 法在数据库IVC、TID2013和CSIQ上的PLCC和SRCC值均达到了 0.920以上。实 验数据表明,本文算法的评价结果准确性好、性能稳定且与人的主观观测结果的一致性高。     

基于组合矩的激光雷达距离像目标识别

激光成像雷达距离像与目标表面物理结构特性密切相关,体现目标的本质特征,是目标识别的主要研究方向。采用组合矩的神经网络方法进行了相干激光雷达距离像目标识别仿真研究。用Hu不变矩和仿射不变矩两者的低阶矩组合表示距离像目标区域特征,利用反向传播(BP)神经网络识别不同方位角的车辆。当视场角不变时,训练10个目标,每个目标取3～19个样本,在不同载噪比(CNR)情况下,分析Hu不变矩、仿射不变矩和两者组合矩的识别率。理论分析和仿真实验表明利用组合不变矩进行距离像目标识别性能优于单独利用其中一种不变矩。     

Image analysis by Gaussian-Hermite moments

Orthogonal moments are powerful tools in pattern recognition and image processing applications. In this paper, the Gaussian-Hermite moments based on a set of orthonormal weighted Hermite polynomials are extensively studied. The rotation and translation invariants of Gaussian-Hermite moments are derived algebraically. It is proved that the construction forms of geometric moment invariants are valid for building the Gaussian-Hermite moment invariants. The paper also discusses the computational aspects of Gaussian-Hermite moment, including the recurrence relation and symmetrical property. Just as the other orthogonal moments, an image can be easily reconstructed from its Gaussian-Hermite moments thanks to the orthogonality of the basis functions. Some reconstruction tests with binary and gray-level images (without and with noise) were performed and the obtained results show that the reconstruction quality from Gaussian-Hermite moments is better than that from known Legendre, discrete Tchebichef and Krawtchouk moments. This means Gaussian-Hermite moment has higher image representation ability. The peculiarity of image reconstruction algorithm from Gaussian-Hermite moments is also discussed in the paper. The paper offers an example of classification using Gaussian-Hermite moment invariants as pattern feature and the result demonstrates that Gaussian-Hermite moment invariants perform significantly better than Hu's moment invariants under both noise-free and noisy conditions.     

Color image detail enhancement based on quaternion guided filter

Color image enhancement is an active research field in image processing. Currently, many image enhancement methods are capable of enhancing the details of the color image. However, these methods only process the red, green and blue (RGB) color channels separately, which leads to color distortion easily. In order to overcome this problem, the paper presents an approach to integrate the quaternion theory into the traditional guided filter to obtain a quaternion guided filter (QGF). This method makes full use of the color information of an image to realize the holistic processing of RGB color channels. So as to preserve color information while enhancing details, this paper proposes a color image detail enhancement algorithm based on the QGF. Experimental results show that the proposed algorithm is effective in the applications of the color image detail enhancement, and enables image's edges to be more prominent and texture clearer while avoiding color distortion. Compared with the existing image enhancement methods, the proposed method achieves better enhancement performance in terms of the visual quality and the objective evaluating indicators.     

Color image processing by using binary quaternion-moment-preservingthresholding technique

This paper presents a new moment-preserving thresholding technique, called the binary quaternion-moment-preserving (BQMP) thresholding, for color image data. Based on representing color data by the quaternions, the statistical parameters of color data can be expressed through the definition of quaternion moments. Analytical formulas of the BQMP thresholding can thus be determined by using the algebra of the quaternions. The computation time for the BQMP thresholding is of order of the data size. By using the BQMP thresholding, quaternion-moment-based operators are designed for the application of color image processing, such as color image compression, multiclass clustering of color data, and subpixel color edge detection. The experimental results show that the proposed operator for color image compression can have output picture quality acceptable to human eyes. In addition, the proposed edge operator can detect the color edge at the subpixel level. Therefore, the proposed BQMP thresholding can be used as a tool for color image processing.     

Radial Tchebichef moment invariants for image recognition

Radial Tchebichef moments as discrete orthogonal moments in the polar coordinate have been successfully used in the field of image recognition. However, the scale invariant property of these moments has not been studied due to its complexity of the problem. In this paper, we present a method to construct a set of scale and rotation invariants extracted from radial Tchebichef moments, named radial Tchebichef moment invariants (RTMI). Experimental results show the efficiency and the robustness to noise of the proposed method for recognition tasks.     

Quaternion pseudo-Zernike moments combining both of RGB information and depth information for color image splicing detection

The quaternion representation (QR) used in current quaternion-based color image processing creates redundancy when representing a color image of three components by a quaternion matrix having four components. In this paper, both RGB and depth (RGB-D) information are considered to improve QR for efficiently representing RGB-D images. The improved QR fully utilizes the four-dimensional quaternion domain. Using this improved QR, firstly we define the new quaternion pseudo-Zernike moments (NQPZMs) and then propose an efficient computational algorithm for NQPZMs through the conventional pseudo-Zernike moments (PZMs). Finally, we propose an algorithm for color image splicing detection based on the NQPZMs and the quaternion back-propagation neural network (QBPNN). Experimental results on four public datasets (DVMM, CASIA v1.0 and v2.0, Wild Web) demonstrate that the proposed splicing detection algorithm can achieve almost 100% accuracy with the appropriate feature dimensionality and outperforms 14 existing algorithms. Moreover, the comparison of six color spaces (RGB, HSI, HSV, YCbCr, YUV, and YIQ) shows that the proposed algorithm using YCbCr color space has the overall best performance in splicing detection.     

Image analysis by Krawtchouk moments

A new set of orthogonal moments based on the discrete classical Krawtchouk polynomials is introduced. The Krawtchouk polynomials are scaled to ensure numerical stability, thus creating a set of weighted Krawtchouk polynomials. The set of proposed Krawtchouk moments is then derived from the weighted Krawtchouk polynomials. The orthogonality of the proposed moments ensures minimal information redundancy. No numerical approximation is involved in deriving the moments, since the weighted Krawtchouk polynomials are discrete. These properties make the Krawtchouk moments well suited as pattern features in the analysis of two-dimensional images. It is shown that the Krawtchouk moments can be employed to extract local features of an image, unlike other orthogonal moments, which generally capture the global features. The computational aspects of the moments using the recursive and symmetry properties are discussed. The theoretical framework is validated by an experiment on image reconstruction using Krawtchouk moments and the results are compared to that of Zernike, pseudo-Zernike, Legendre, and Tchebyscheff moments. Krawtchouk moment invariants are constructed using a linear combination of geometric moment invariants; an object recognition experiment shows Krawtchouk moment invariants perform significantly better than Hu's moment invariants in both noise-free and noisy conditions.