An algorithm for segmentation of lung ROI by mean-shift clustering combined with multi-scale HESSIAN matrix dot filtering

A new algorithm for segmentation of suspected lung ROI(regions of interest)by mean-shift clustering and multi-scale HESSIAN matrix dot filtering was proposed.Original image was firstly filtered by multi-scale HESSIAN matrix dot filters,round suspected nodular lesions in the image were enhanced,and linear shape regions of the trachea and vascular were suppressed.Then,three types of information,such as,shape filtering value of HESSIAN matrix,gray value,and spatial location,were introduced to feature space.The kernel function of mean-shift clustering was divided into product form of three kinds of kernel functions corresponding to the three feature information.Finally,bandwidths were calculated adaptively to determine the bandwidth of each suspected area,and they were used in mean-shift clustering segmentation.Experimental results show that by the introduction of HESSIAN matrix of dot filtering information to mean-shift clustering,nodular regions can be segmented from blood vessels,trachea,or cross regions connected to the nodule,non-nodular areas can be removed from ROIs properly,and ground glass object(GGO)nodular areas can also be segmented.For the experimental data set of 127 different forms of nodules,the average accuracy of the proposed algorithm is more than 90%.

HESSIAN MATRIX BASED SADDLE POINT DETECTION FOR GRANULES SEGMENTATION IN 2D IMAGE

Segmenting the touching objects in an image has been remaining as a hot subject due to the problematic complexities, and a vast number of algorithms designed to tackle this issue have come into being since a decade ago. In this paper, a new granule segmentation algorithm is developed using saddle point as the cutting point. The image is binarized and then sequentially eroded to form a gray-scale topographic counterpart, followed by using Hessian matrix computation to search for the saddle point. The segmentation is performed by cutting through the saddle point and along the maximal gradient path on the topographic surface. The results of the algorithm test on the given real images indicate certain superiorities in both the segmenting robustness and execution time to the referenced methods.

Least-squares reverse time migration method using the factorization of the Hessian matrix

Least-squares reverse time migration(LSRTM)can eliminate imaging artifacts in an iterative way based on the concept of inversion,and it can restore imaging amplitude step by step.LSRTM can provide a high-resolution migration section and can be applied to irregular and poor-quality seismic data and achieve good results.Steeply dipping refl ectors and complex faults are imaged by using wavefi eld extrapolation based on a two-way wave equation.However,the high computational cost limits the method’s application in practice.A fast approach to realize LSRTM in the imaging domain is provided in this paper to reduce the computational cost signifi cantly and enhance its computational effi ciency.The method uses the Kronecker decomposition algorithm to estimate the Hessian matrix.A low-rank matrix can be used to calculate the Kronecker factor,which involves the calculation of Green’s function at the source and receiver point.The approach also avoids the direct construction of the whole Hessian matrix.Factorization-based LSRTM calculates the production of low-rank matrices instead of repeatedly calculating migration and demigration.Unlike traditional LSRTM,factorization-based LSRTM can reduce calculation costs considerably while maintaining comparable imaging quality.While having the same imaging eff ect,factorization-based LSRTM consumes half the running time of conventional LSRTM.In this regard,the application of factorization-based LSRTM has a promising advantage in reducing the computational cost.Ambient noise caused by this method can be removed by applying a commonly used fi ltering method without signifi cantly degrading the imaging quality.

Research on Image Quality Enhancement Algorithm Using Hessian Matrix

The Hessian matrix has a wide range of applications in image processing,such as edge detection,feature point detection,etc.This paper proposes an image enhancement algorithm based on the Hessian matrix.First,the Hessian matrix is obtained by convolving the derivative of the Gaussian function.Then use the Hessian matrix to enhance the linear structure in the image.Experimental results show that the method proposed in this paper has strong robustness and accuracy.

基于Hessian矩阵的改进EDlines输电线识别算法

随着电力网络的飞速发展,采用无人机搭载高清摄像头来进行输电线巡检已成常态。为提高巡检的实时性和准确性,本研究提出了一种基于Hessian矩阵的改进EDlines输电线识别算法。首先,通过伽马变换对输电线图像进行预处理,利用Hessian矩阵特征值和特征向量以求取像素点主方向和主曲率,并获得输电线主体轮廓,从而摒弃了传统方法中梯度计算锚点和像素方向的繁琐步骤。接着,在主体轮廓基础上连接锚点以得到潜在直线线段像素链,并运用随机抽样一致性(RANSAC)算法来进行线段拟合。最后,根据直线间的距离和角度,迭代拟合以得到最终的输电线。实验结果表明,该方法能应对多种复杂环境下的输电线识别任务,抗干扰能力强,误检率显著降低,为高空输电线巡检提供了可靠的技术支持,具有重要的工程应用价值。

基于Hessian自适应增强的口腔结构光图像处理

为提升重建的牙齿三维点云的精度,解决口水、牙釉质等环境因素导致的结构光口腔扫描仪采集的条纹图像质量较差的问题,首先引入一种自适应中值广义总变分融合滤波方法来抑制噪声,并且有效保留图像细节信息;在此基础上提出一种基于Hessian矩阵特征值的自适应线性结构增强算法用于增强二维结构光图像中的条纹信息,算法根据统计的局部特征,自适应调整增强参数。实验结果表明,与传统Hessian增强方法相比,自适应Hessian增强后的条纹图像的熵增强函数(EMEE)和信息熵更高,得到的三维点云有更完整的细节特征和更高的匹配精度。

基于机器视觉的汽车压装衬套偏转角度测量

衬套安装的角度测量对于确保压装过程中汽车悬架与衬套的准确组装十分重要,现有的单目测量方法由于存在相机安装环境受限、测量准确率低的缺点而难以广泛应用。为提高衬套偏转角度的测量准确性,提出了一种基于特征匹配与径向基神经网络的衬套偏转角度测量方法。采用Hessian矩阵优化ORB算法,剔除误匹配对,提高ORB算法匹配性能;采用基准模板匹配策略,解决相机斜视状态下图像特征被遮挡导致的无法匹配问题,并将采集图像的特征点转换至基准模板上;通过引入径向基函数神经网络进行偏转角度软测量,拟合特征点与偏转角度的非线性关系,提高衬套偏转角度测量的精度。实验结果表明,所研究方法可以有效进行偏转角度测量,最大平均相对误差为2.72%,满足衬套偏转角度测量要求,在汽车生产过程中有一定的应用价值。

基于Hessian矩阵的中心路径提取算法

虚拟内窥镜可用来对人体内部管腔结构进行无损检测,在医疗诊断及手术上有着重要意义.要想快速准确地进行虚拟内窥漫游,一个首要的步骤是要先提取出模型的中心线以指导视点的移动.提出了一种基于Hessian矩阵的中心路径提取算法.在距离变换的基础上,先利用Hessian矩阵的几何意义找出中心线的大致形状作为初始路径;然后进行可视性检测以确定最终的路径点,可视球的半径通过Hessian矩阵的特征值自适应地确定;最后用最短路径生成算法得到模型的中心路径.实验结果表明了该算法的有效性.

基于Hessian内点法的微型能源网日前冷热电联供经济优化调度

微型能源网包含冷、热、电和气4种能源形式,具有负荷种类多样、供能设备丰富的特点。在对微型能源网内多种供能及蓄能设备进行建模的基础上,提出基于集中互连能源交换网络的冷热电联供微型能源网的供能架构,架构内冷热电负荷被细分为纯电负荷、热水负荷、空间热负荷、冷冻制冷负荷和空间冷负荷,围绕该架构建立冷热电联供微型能源网经济优化调度模型,采用基于Hessian矩阵迭代的内点法对模型进行了求解。算例表明,通过调度微型能源网内各供能设备的运行方式和出力,可以显著降低系统的日运行费用,实现冷热电联供微型能源网的经济优化运行,得出的合理调度方案证实了所提模型和求解方法的正确性及有效性。

基于Hessian矩阵和熵的CT序列图像裂缝分割方法

工业CT序列图像的各向不同性和伪影会影响裂缝分割精确度和准确度,因此提出一种基于Hessian矩阵和熵的各向不同性工业CT序列图像裂缝自动分割方法。首先,用基于Hessian矩阵的多尺度线状滤波增强裂缝区域,抑制非线状区域;然后,建立一种新的二维直方图,获取滤波之后层内和层间的信息;再根据直方图的最大类熵确定阈值区间,最终得到裂缝的二值化分割结果。实验表明,所提方法不仅能够满足实际工业CT序列图像裂缝分割中精确、自动的分割要求,而且相较其他4种已有方法,能够得到更完整、更准确的分割结果。

基于Hessian矩阵和支持向量机的CT图像裂纹分割

工业CT裂纹分割是工业CT图像处理中的一项关键技术,而CT图像中的伪影、噪声等干扰会对裂纹分割带来极大的困扰。为了提高CT图像中裂纹的分割精度,本文通过分析CT图像中裂纹的特征,提出了结合Hessian矩阵和支持向量机的CT图像裂纹识别与分割的方法。首先采用基于Hessian矩阵的多尺度滤波方法提取CT图像中的线状结构并对提取的线状结构进行对比度增强;然后利用图像像素点灰度在空间的分布规律提取线状结构图像的纹理特征信息;再使用基于径向基函数的支持向量机训练裂纹识别分类器;进而使用训练好的模型定位测试图像中裂纹所在的方块区域;最后使用自动阈值分割算法得到CT图像中的裂纹。实验结果表明,结合Hessian矩阵和支持向量机的分割方法能够抑制图像中非目标区域,提高了算法的抗干扰性,对裂纹子图像识别的准确率可达94.5%,具有实际的工程应用价值。

基于多尺度Hessian矩阵和Gabor滤波的造影图像冠脉中心线提取

目的提取冠脉造影图像中血管的中心线。方法提出一种基于Hessian矩阵和Gabor滤波的血管中心线提取算法,该算法首先利用Hessian矩阵将血管提取,然后根据Gabor滤波器的方向响应特性利用跟踪策略对细化后的血管图像进行校正,得到血管中心线,并提出了精度评价方法。结果将该算法用于随机抽取的图像,均取得高精度的血管中心线以及较理想的血管宽度。结论该算法对于造影图像冠脉中心线提取精度较高,并能同时求得血管宽度。

Kinematics and Dynamics Hessian Matrices of Manipulators Based on Screw Theory

The complexity of the kinematics and dynamics of a manipulator makes it necessary to simplify the modeling process.However,the traditional representations cannot achieve this because of the absence of coordinate invariance.Therefore,the coordinate invariant method is an important research issue.First,the rigid-body acceleration,the time derivative of the twist,is proved to be a screw,and its physical meaning is explained.Based on the twist and the rigid-body acceleration,the acceleration of the end-effector is expressed as a linear-bilinear form,and the kinematics Hessian matrix of the manipulator（represented by Lie bracket）is deduced.Further,Newton-Euler＇s equation is rewritten as a linear-bilinear form,from which the dynamics Hessian matrix of a rigid body is obtained.The formulae and the dynamics Hessian matrix are proved to be coordinate invariant.Referring to the principle of virtual work,the dynamics Hessian matrix of the parallel manipulator is gotten and the detailed dynamic model is derived.An index of dynamical coupling based on dynamics Hessian matrix is presented.In the end,a foldable parallel manipulator is taken as an example to validate the deduced kinematics and dynamics formulae.The screw theory based method can simplify the kinematics and dynamics of a manipulator,also the corresponding dynamics Hessian matrix can be used to evaluate the dynamical coupling of a manipulator.

基于Hessian矩阵本征分解的目标中心线提取算法

在对动态目标闭环跟踪过程中,目标中心线的提取对目标的定位以及实时姿态判定有着重要影响,是实现高精度定位以及姿态判定的重要依据。根据Hessian矩阵在微分几何中的意义以及动态目标的成像特点,提出一种基于Hessian矩阵本征分解的目标中心线提取算法。算法在分割出目标的基础上,进行欧氏距离变换并建立关于目标的灰度Hessian矩阵,对Hessian矩阵进行本征分解,获取目标中心的初始点集,对这一点集采用随机采样一致算法进行野值剔除,最终拟合出目标的中心线。为了验证算法的有效性,设置了评价机制,并和前人提出的若干算法进行了对比,仿真实验表明该算法具有较高的稳定性和准确性。

一种新的血管造影图像Hessian矩阵增强算法

针对实际血管造影图像存在的噪声和光照不均,本文提出一种新的Hessian矩阵增强算法来提取血管图像。算法主要通过无抽样方向滤波器组进行血管方向图分解、同态滤波器滤波、Hessian特征矩阵和血管方向图合成。实验表明,与传统Hessian算法相比,提出的算法能够连续提取血管的精细结构,对噪声不敏感,处理的图像质量更高。

基于Hessian算子的多尺度视网膜血管增强滤波方法

提出一种基于Hessian矩阵的多尺度视网膜血管集成增强滤波算法。将Hessian矩阵的特征值和特征向量应用于血管特征的响应函数及形态学和非线性各向异性扩散处理的各个环节,选择合理的尺度空间范围及尺度空间增量和调节因子进而达到平滑非线状区域和锐化增强血管区域的效果。与其他血管增强方法相比,该方法在同等准确率下具有较高的稳定鲁棒性。

基于Hessian特征的视网膜血管图像的增强滤波算法

提出了一种基于Hessian特征的视网膜血管图像的增强滤波算法,分析了Hessian特征值对各类形状的抑制和加强作用,将Hessian矩阵的特征值与特征向量应用于视网膜血管特征的响应函数及形态学和非线性扩散处理的各个环节,并选择合理的尺度空间范围和尺度空间增量,调节因子而平滑非线状区域和锐化增强血管区域,本文算法在同等准确率下具有较高的稳定鲁棒性。

基于Hessian矩阵的黑白棋盘格角点检测

针对棋盘格角点的检测,提出了一种运算速度快、定位精度高的Hessian矩阵子像素角点检测算法。简述了Hessian矩阵的原理、算法的执行流程和黑白棋盘格子像素坐标提取的基本方法。通过实验检测出了黑白棋盘格中的角点,得到了角点坐标,并利用二阶泰勒展开式得到了角点的子像素坐标。最后,在不同的噪声水平下,与Harris算法作比较,计算出提取误差与提取时间。实验证明,Hessian矩阵对黑白棋盘格角点检测得更加精确。该实验结果可应用于摄像机标定中。

基于Hessian矩阵和水平集的视网膜血管分割

视网膜血管图像可以作为糖尿病与青光眼等疾病的诊断依据;但现有的血管提取算法存在精度不足、对噪声敏感,以及鲁棒性不强等缺点。针对这个问题提出了一种新的视网膜血管图像分割方法。首先获取视网膜绿色通道图像,利用Hessian矩阵特征值、特征向量的几何特性和响应函数,初步估计视网膜图像中可能存在的血管;并在此基础上利用水平集函数初始化血管图像。然后,在局部数据能量拟合泛函中引入新的正则化和面积约束。最后,在水平集函数演化过程中获得精准的视网膜血管图像。实验表明算法在分割视网膜血管图像上具有较强的鲁棒性。

基于Hessian矩阵的多尺度视网膜图像增强方法

眼底视网膜图像的血管增强在眼科诊断中具有广泛的研究价值。提出了一种基于Hessian矩阵的多尺度血管增强方法,给出了应用的方案和过程,并在DRIVE眼底图像数据库上进行实验。与其他血管增强方法相比,该方案可达到相当的准确率,且在同等准确率下具有较高的鲁棒性。