一种新颖的手形特征提取算法

基于手形的生物特征识别技术,利用人手的矢量和点特征自动实现个人身份的鉴别.由于手形特征相对简单,目前手形只用于身份认证.本文旨在充分利用手形信息,提出了一种新颖的手形特征提取算法,准确提取手指的关键特征点,提高了手形特征的提取准确率.     

指纹网络身份认证系统中关键技术的研究

针对日益突出的互联网安全问题,介绍了指纹网络身份认证系统的功能,对身份认证系统网络拓扑结构进行了详细的研究,并结合了指纹提取方法,提出了一种基于中间点向量的指纹匹配参考点对的选择方法.在C#语言编程平台上对指纹识别算法进行了实验,实验结果表明提出的指纹识别算法能够提取指纹特征并给出指纹匹配结果.     

基于空间约束的快速鲁棒特征匹配优化

该文提出一种基于空间约束的快速鲁棒特征(SURF)匹配优化算法,称为SC-SURF。首先通过SURF算法检测和匹配图像的特征点。然后根据最近邻比例越低其匹配精度越高的特点,得到按最近邻比率排序的匹配点。并以最优匹配点作为参考点生成新的坐标系,利用空间位置关系地图对每对匹配点进行编码。同时为了简化随机抽样一致性(RANSAC)算法,选择尽量少的最优匹配点对作为RANSAC的代表测试数据集,并由该测试数据集拟合目标投影变换矩阵。最后结合匹配点间的空间位置关系和简化的RANSAC算法对匹配点进行几何校验。实验表明该方法在达到良好匹配精度的同时,具有鲁棒性强,匹配速度快的优点。     

基于图像配准的指静脉身份认证技术

手指静脉在采集时手指旋转和姿态改变导致静脉形变和图像阴影,影响手指静脉身份验证的准确性。因此,文中提出一种基于图像配准的指静脉认证方法,通过少量稳定特征点配准认证图像,并提取两幅配准图像的纹理特征进行身份验证。该方法首先选择邻域清晰度高的静脉叉点作为特征点,然后对特征点进行匹配,并将两幅图像配准,最后根据纹理特征计算两幅配准图像的相似度。所提方法主要克服了基于特征点匹配的方法中点对数量少的问题,并解决了静脉形变的问题。实验结果证明,该方法较模板匹配和特征点匹配方法具有良好的性能。     

基于人体手指静脉特征的身份认证系统设计

针对指纹识别、手形识别、虹膜识别、人脸识别等常见的生物认证技术的缺点,文章深入研究了一种基于人体手指静脉特征的身份认证方法。根据手指静脉不同区域灰度差别较大的特点,提出了一种分区域处理与形态学图像处理相结合的方法,分离出了静脉和背景,并且为了减少系统响应时间,引入了将图像归一化的思想;最后,将手指静脉纹路进行了细化,并用模板匹配识别的方法实现了整个系统的设计初衷。     

一种视觉导航影像特征点整体匹配算法

视觉导航领域已有的影像特征点匹配算法主要基于描述子的相似性度量,由于需要大量特征点且缺少对影像整体特征的考虑,影像匹配的实时性和可靠性受到影响。为此,提出一种基于聚类分析的影像特征点整体匹配算法。该算法对特征点集进行基于距离的聚类分析筛选出具有代表性且重复率较高的特征点,参考特征点分布情况将目标影像和待匹配影像剖分为4个区域,从每个区域随机选取两个特征点计算基本矩阵,基于核线约束和位置约束进行特征点的整体匹配并依据特征点间的几何相似性对匹配结果进行检核。选取慕尼黑工业大学彩色-深度数据集、无人机、移动机器人拍摄的影像进行影像匹配试验,结果表明,提出算法匹配正确率高达到97.1%,平均匹配时间小于25 ms,可以满足实时匹配的要求。     

基于零信任安全架构的网络用户身份跨域匹配

不同网络域数据互通性差,导致网络主机难以实现用户身份跨域匹配和认证,提出基于零信任安全架构的网络用户身份跨域匹配方法。按照零信任安全架构部署原则,定义用户身份属性,提取用户行为轨迹特征,完成网络用户身份建模。根据用户身份建模结果,将应用网络划分成多个功能区域,通过设置跨域认证协议的方式,确定匹配调用链码的计算表达式,实现网络用户身份跨域匹配。实验结果表明,在零信任安全架构支持下,所选七组用户身份信息的跨域认证结果与网络ID原码完全一致,匹配成功率高达100%,有效提升了网络主机对于用户身份跨域匹配和认证能力。     

基于注意力机制的特征点匹配网络的SLAM方法

已有的实时定位与地图构建(simultaneous localization and mapping,SLAM)方案采用的特征点匹配方法普遍会受视角变化的影响使得特征点的匹配比较困 难,进而 干扰到特征点匹配的精度,最终影响到三维(three-dimensional, 3D) 点云地图构建以及相机运动位姿估计的精度。为 此,本文提出 一种基于注意力机制的特征点匹配网络的SLAM方法。相比于现有的SLA M方法,本 文将SLAM中视觉里程计模块的特征点匹配的方法替换成了一个全新的、基于注意力机制的 特征点匹配网 络的特征点匹配方法,并和传统的特征点提取方法做了一个全新的特征点提取与匹配的组合 ,形成了一个 新的视觉里程计,进而形成了一个新的SLAM方法。首先,通过传统的特征点提取算法进行 特征点的提取, 对提取的特征点及描述子向量进行编码,通过图注意力神经网络进行学习得到匹配描述子, 根据匹配描述 子创建得分矩阵,采用最优传输算法求解最优得分矩阵,计算得到最优匹配点对,到这里就 完成了特征点 提取与匹配的整个过程;基于匹配点对完成相机的定位、建图和回环检测。本文采用KITT I公开数据集 进行实验,实验结果表明采用基于注意力机制特征点匹配网络的SLAM方案,在视角变化不 稳定的情况下,相机运动轨迹误差和相机位姿估计误差的精度明显有所提升。     

基于特征点对齐度的图像配准方法

该文提出了一个新的匹配准则特征点对齐度准则,并在此基础上提出了一种基于特征点对齐度准则的图像配准方法。首先,利用小波多尺度积提取出图像的特征点及其角度信息,再利用该文提出的特征点对齐度准则计算所有特征点对之间的对齐度,从而得到匹配点对。实验结果证明了该方法的精确性和有效性。     

宇宙通信、星际通信、卫星通信与多址通信

0617638TD再励学习在卫星姿态控制中的应用〔刊,中〕/刘向东//北京理工大学学报.—2006,26(3).—248-250(L)0617639基于特征点集的匹配算法应用于卫星姿态确定〔刊,中〕/蔡晓东//北京航空航天大学学报.—2006,32(2).—171-175(L)综合了灰度与几何特征匹配方法,依据局部纹理能量分布选取特征点集,并利用特征点集的几何约束关系构建了可描述图像特征的模板。通过逐步求精方法实现了实时图像与基准图像的匹配。首先通过特征点集匹配进行粗搜索;然后通过精搜索以及角度较正得到实时图像中目标偏移旋转量。该特征点集算法与传统图像匹配算法相…     

基于多分类的虹膜匹配方法

在传统的虹膜识别系统中,虹膜匹配被认为是一个二分类问题：类内匹配和类间匹配。许多已存在的方法简单地利用距离来执行虹膜匹配。由于这些方法不能很好地利用虹膜特征,所以会产生很高的拒识率和误识率,且鲁棒性不强。为了解决这些问题,提出把虹膜匹配当作一个多分类问题,采用一种新颖的蕨算法（Ferns）分类器来完成该工作。相比支持向量机（SVM）分类器,在执行虹膜匹配时,Ferns分类器有诸多优点。为了对提出的算法给出全面评价,实验中分别在认证和识别这2种模式下对该算法进行测试。实验结果证明,提出的方法可以极大地改善虹膜识别系统的性能。     

基于同底三角形面积描述的形状检索

为了在形状匹配的过程中提高形状特征对边界噪声和图像变形的鲁棒性,同时兼顾形状匹配算法的检索精度和运算效率,提出一种基于同底三角形面积的形状匹配方法.该方法首先计算每个轮廓采样点的同底三角形面积描述子,并对该描述子进行局部平滑,使其更加鲁棒.然后采用加权L1度量方法计算两个形状所有轮廓点的同底三角形描述子之间的距离,获得匹配代价矩阵.最后利用动态规划算法计算匹配代价矩阵的相似度,获得形状距离,实现形状匹配.通过在MPEG-7、Kimia以及铰接形状数据库上测试分析表明,该方法对变形目标具有良好的鲁棒性,且提高了运算效率和检索精度.     

Objects Matching using Optimization Techniques

In this work, the objects matching problem (composed by data points) is solved as a global optimization problem. The proposed solution is compared with a previously developed one, based on a local approach. With this comparison, the significant improvement of the results is confirmed. In this paper, two previously developed methodologies for obtaining the quantification of the affinities between the data points are also presented. One of these methodologies is based on the modal analysis of the shapes of the objects, while the other one uses the finite elements method and the modal analysis. Usually, the existing solutions for matching problems allow only matches of type "one with one". However, there are many applications in which this type of matching is not adequate as it can imply loss of information. To overcome this problem, an applicable solution was developed for contour objects. This solution allows the adequate matching of the excess points, getting correspondences of type "one with several" or vice versa.     

Multimodality Image Registration Using Spatial Procrustes Analysis and Modified Conditional Entropy

In this paper, we propose a new image registration technique using two kinds of information known as object shapes and voxel intensities. The proposed approach consists of two registration steps. First, an initial registration is carried out for two volume images by applying Procrustes analysis theory to the two sets of 3D feature points representing object shapes. During this first stage, a volume image is segmented by using a geometric deformable model. Then, 3D feature points are extracted from the boundary of a segmented object. We conduct an initial registration by applying Procrustes analysis theory with two sets of 3D feature points. Second, a fine registration is followed by using a new measure based on the entropy of conditional probabilities. Here, to achieve the final registration, we define a modified conditional entropy (MCE) computed from the joint histograms for voxel intensities of two given volume images. By using a two step registration method, we can improve the registration precision. To evaluate the performance of the proposed registration method, we conduct various experiments for our method as well as existing methods based on the mutual information (MI) and maximum likelihood (ML) criteria. We evaluate the precision of MI, ML and MCE-based measurements by comparing their registration traces obtained from magnetic resonance (MR) images and transformed computed tomography (CT) images with respect to x-translation and rotation. The experimental results show that our method has great potential for the registration of a variety of medical images.     

基于边缘修正的高光谱图像超像素空谱核分类方法

本文提出了一种边缘修正的超像素空间光谱核分类方法,该方法能够有效解决构建空谱核时超像素方法提取的空间信息完全依赖于同一个超像素特征,边缘处像素空间信息刻画不准确这一缺陷,从而有效提升分类精度.首先本文提出一种固定窗口与超像素结合的同质区域选择方法,对提取的邻域像素进行赋权,将超像素中固定窗口外的像素权值置零,得到修正的空间光谱核;其次,进一步考虑相邻超像素之间的相关性,得到相邻超像素间的空间特征光谱核,并与上一步中的空间光谱核进行凸组合得到修正的超像素空间光谱核,最后采用支持向量机进行分类.真实高光谱数据实验结果表明：本文方法能有效克服超像素空谱核的空间信息不稳定性,分类精度优于现有的最新的分类方法.     

一种基于各向异性尺度空间的SAR图像匹配算法

针对斑点噪声对合成孔径(SAR)图像匹配算法的影响,提出了一种基于各向异性尺度空间的SAR图像匹配算法。首先,采用加性算子分裂算法解方案来构建各向异性尺度空间,在滤除斑点噪声的同时更好地保留图像细节;然后,在非线性尺度空间中提取特征点,并采用改进的SURF描述子描述特征,弱化斑点噪声对匹配的影响;最后,采用变换参数约束策略筛选匹配点对,提高匹配正确率。该方法既保持了同名点的精度还增加了同名点的数量,通过对不同极化、时相、波段以及不同视角下多种地物的匹配实验,验证了该方法的优越性。     

An accurate traffic classification model based on support vector machines

Network traffic classification is a fundamental research topic on high‐performance network protocol design and network operation management. Compared with other state‐of‐the‐art studies done on the network traffic classification, machine learning (ML) methods are more flexible and intelligent, which can automatically search for and describe useful structural patterns in a supplied traffic dataset. As a typical ML method, support vector machines (SVMs) based on statistical theory has high classification accuracy and stability. However, the performance of SVM classifier can be severely affected by the data scale, feature dimension, and parameters of the classifier. In this paper, a real‐time accurate SVM training model named SPP‐SVM is proposed. An SPP‐SVM is deducted from the scaling dataset and employs principal component analysis (PCA) to extract data features and verify its relevant traffic features obtained from PCA. By employing PCA algorithm to do the dimension extraction, SPP‐SVM confirms the critical component features, reduces the redundancy among them, and lowers the original feature dimension so as to reduce the over fitting and increase its generalization effectively. The optimal working parameters of kernel function used in SPP‐SVM are derived automatically from improved particle swarm optimization algorithm, which will optimize the global solution and make its inertia weight coefficient adaptive without searching for the parameters in a wide range, traversing all the parameter points in the grid and adjusting steps gradually. The performance of its two‐ and multi‐class classifiers is proved over 2 sets of traffic traces, coming from different topological points on the Internet. Experiments show that the SPP‐SVM's two‐ and multi‐class classifiers are superior to the typical supervised ML algorithms and performs significantly better than traditional SVM in classification accuracy, dimension, and elapsed time.     

Polygonal Approximation of Digital Curves to Preserve Original Shapes

In this letter, we propose a novel polygonal approximation of digital curves that preserve original shapes. The proposed method first detects break points, which have two different consecutive vectors, and sets an initial dominant point set. The approximation is then performed iteratively by deleting a dominant point using a novel distance, which can measure both the distance and the angle acuteness. The experimental results show that the proposed method can preserve original shapes and is appropriate for various shapes, including slabsided shapes.