一种构造人脸原型的Face-LS算法

将Loop细分原则引入语音驱动的语音动画合成系统中,提出并设计一种基于局部细分模型构造人脸原型的Face-LS算法。算法利用局部细分原则在脸部网格的局部区域上进行迭代插值,经插值细分后在降低整体网格密度的前提下,导致不同脸部区域特征点密度不同,使重要区域具有较高密度,以此降低脸部原型的褶皱度。通过仿真试验验证该算法具有较好的性能。     

基于局部重建的点云特征点提取

为了有效地提取点云数据中的特征信息,针对采自分片光滑曲面的散乱点云数据,提出一种基于局部重建的鲁棒特征点提取方法.首先基于局部邻域的协方差分析计算每个数据点的特征度量,并通过阈值过滤获取初始特征点集合;然后在每个初始特征点的局部邻域内构建不跨越特征区域,以反映该点局部特征信息的三角形集合;再利用共享近邻算法对构造的三角形法向进行聚类,得到对应局部区域数据点的分类集合;最后对每一类点集拟合平面,通过判断该点是否同时落在多个平面来进行特征点提取.实验结果表明,该方法简单、稳定,对局部邻域选取的大小不敏感,具有一定的抗噪能力;能够在有效提取显著特征的同时,尽可能多地保留相对较弱的特征.     

基于特征点集GABC算法的WSN覆盖优化

针对人工蜂群算法利用网格点计算网络覆盖率会导致计算量大且容易陷入局部最优解的问题,提出一种基于特征点集的全局最优解人工蜂群算法优化无线传感器网络。首先将目标区域划分成有限个特征点,用传感器对特征点的覆盖来转化为对若干特征点的覆盖计算,减少求解覆盖率的计算量,进而描述整个网络的覆盖情况。然后在特征点集的基础上,将全局最优解人工蜂群算法成功应用在网络覆盖领域,并且重点对比标准人工蜂群算法和基于全局最优解人工蜂群算法在网络覆盖上的性能。仿真实验结果表明基于全局最优解人工蜂群算法优化节点覆盖后,覆盖率得到有效的提升且不易陷入局部最优解。     

鲁棒拉普拉斯特征映射算法*

研究拉普拉斯特征映射算法（Laplacian eigenmap,LE）对离群点的敏感性,提出一种具有鲁棒性的拉普拉斯特征映射算法（robust Laplacian eigenmap,RLE）。该方法在离群点检测的基础上,利用鲁棒PCA算法（robust PCA,RPCA）对离群点进行局部光滑化处理,将离群点和其邻域投影到低维的局部切空间上,再构造能够准确反映离群点局部邻域关系的对应权值,减少离群点对Laplacian矩阵的影响。模拟实验和实际例子都证明,通过这种方法构造的鲁棒拉普拉斯特征映射算法,对于离群     

核仿射子空间最近点分类算法

受支持向量机的几何解释和最近点问题启发,提出一种新型的模式分类算法——核仿射子空间最近点分类算法。该算法在核空间中,将支持向量机几何模型中的最近点搜索区域由2类训练特征集凸包推广到2类特征样本各自生成的仿射子空间,以仿射子空间作为特征样本分布的粗略估计,通过仿射子空间中的最近的2个点构造平分仿射子空间间隔的最优分类超平面。该算法在ORL人脸识别数据库上的比较实验中取得了较好的识别效果。     

基于局部细分构造产品原型的PD-LS算法

将Loop细分原则引入产品设计系统中,提出并设计了一种基于局部细分模型构造产品原型的PD-LS算法。算法利用局部细分原则在产品图形的局部区域上进行迭代插值,经插值细分后,在降低整体网格密度的前提下,致使不同区域特征点密度不同,使重要区域具有较高密度,以此降低产品原型的褶皱度。最后通过仿真实验验证该算法具有较好的性能。     

基于图像特征点的公钥水印算法

对于现在公钥水印算法一些抗几何攻击能力弱的问题,提出一种基于图像特征点的公钥水印算法。通过Harris-Laplace算法提取图像的特征点,构造局部特征区域,并在这些区域内做DCT变换和水印信息的嵌入,使得嵌入水印后的图像可以更好地抗RST攻击。     

基于Grassmann流形的多聚类特征选择

在无监督聚类特征选择过程中,局部欧氏度量可能置乱局部流形的拓扑结构,影响所选特征的聚类性能。为此,提出一种基于Grassmann流形的多聚类特征选择算法。利用局部主成分分析逼近数据点的切空间,获取局部数据的主要变化方向。根据切空间构造Grassmann流形,通过测地距保留局部数据的流形拓扑结构,以L1范数优化逼近流形拓扑,选择利于聚类的原本数据特征。实验结果验证了该算法的有效性。     

基于局部区域动态覆盖的3D点云分类方法

局部几何形状的描述能力, 对不规则的点云形状表示是十分重要的. 然而, 现有的网络仍然很难有效地捕捉准确的局部形状信息. 在点云中模拟深度可分离卷积计算方式, 提出一种新型的动态覆盖卷积(dynamic cover convolution, DC-Conv), 以聚合局部特征. DC-Conv的核心是空间覆盖算子(space cover operator, SCOP), 该算子通过在局部区域中构建各向异性的空间几何体覆盖局部特征空间, 以加强局部特征的紧凑性. DC-Conv通过在局部邻域中动态组合多个SCOP, 实现局部形状的捕捉. 其中, SCOP的注意力系数通过数据驱动的方式由点位置自适应地学习得到. 在3D点云形状识别基准数据集ModelNet40, ModelNet10和ScanObjectNN上的实验结果表明, 该方法能有效提高3D点云形状识别的性能和对稀疏点云的鲁棒性. 最后, 也提供了充分的消融实验验证该方法的有效性. 开源代码发布在https://github.com/changshuowang/DC-CNN.     

基于区域分割和Voronoi图的区域覆盖算法

针对无线传感器网络区域已知的区域覆盖问题,提出了一种基于区域分割和Voronoi图的覆盖算法（RSV）。算法首先分析已知区域的地理信息和兴趣点,根据传感器感知能力,构造合适大小的网格将已知区域细化分割。然后基于分割后的各个区域,根据兴趣点的数量划分其为不同权重部分,并初步设计传感器位置。根据初步部署位置和权重,对不同权重位置构造Voronoi图填补覆盖空洞,直至所有空洞被填补完毕,并为了延长运行寿命设计了合适的节点休眠策略。仿真实验显示,基于区域分割和加权Voronoi图的目标区域覆盖算法相较于现有算法,在节点数量增加较少的情况下,延长了网络的运行寿命,同时使节点能量消耗更加平均,在节点数量受限情况下,算法对有效区域的覆盖效果也更佳。     

A clustering method based on multidimensional texture analysis

Considering the analogy between image segmentation and cluster analysis, the aim of this paper is to adapt statistical texture measures to describe the spatial distribution of multidimensional observations. The main idea is to consider the cluster cores as domains characterized by their specific textures in the data space. The distribution of the data points is first described as a multidimensional histogram defined on a multidimensional regular array of sampling points. In order to evaluate locally a multidimensional texture, a co-occurrence matrix is introduced, which characterizes the local distribution of the data points in the multidimensional data space. Several local texture features can be computed from this co-occurrence matrix, which accumulates spatial and statistical information on the data distribution in the neighborhoods of the sampling points. Texture features are selected according to their ability to discriminate different distributions of data points. The sampling points where the local underlying texture is evaluated are categorized into different texture classes. The points assigned to these classes tend to form connected components in the data space, which are considered as the cores of the clusters.     

半径可调的无线传感器网络三维覆盖算法

针对三维无线传感器网络区域中节点覆盖的问题,提出一种半径可调的无线传感器网络三维覆盖算法（3D-CAAR）。该算法利用虚拟力作用实现无线传感器网络的节点均匀部署,同时结合传感器节点的半径可调覆盖机制,判断节点与被覆盖区域中目标点之间的距离。引入能耗阈值,使得节点根据自身情况调节节点感知半径,从而降低无线传感器网络的整体能耗,提高了节点利用率。最后,通过与传统基于人工势场的三维部署算法（APFA3D）、基于与未知目标精确覆盖的三维算法（ECA3D）仿真实验对比,3D-CAAR的事件集覆盖效能明显较高,能有效解决三维无线传感器网络中对目标节点的覆盖问题。     

基于QR分解的正则化邻域保持嵌入算法

针对训练样本不足时,对数据的低维子空间估计可能会产生严重偏差的问题,提出了一种基于QR分解的正则化邻域保持嵌入算法。首先,该算法定义一个局部拉普拉斯矩阵保留原始数据的局部结构;其次,将类内散度矩阵的特征谱空间划分成三个子空间,通过倒数谱模型定义的权值函数获得新的特征向量空间,进而对高维数据进行预处理;最后,定义一个邻域保持邻接矩阵,利用QR分解获得的投影矩阵和最近邻分类器进行人脸分类。与正则化广义局部保持投影(RGDLPP)算法相比,所提算法在ORL、Yale、FERET和PIE库上识别率分别提高了2个百分点、1.5个百分点、1.5个百分点和2个百分点。实验结果表明,所提算法易于实现,在小样本(SSS)下有较高的识别率。     

两个域上的覆盖粗糙集模型

两个域上的覆盖粗糙集模型推广了一般关系下的粗糙集模型,定义了两个域上的覆盖二元关系,给出了最小子覆盖新的描述,进而得到两个域上基于最小子覆盖的粗糙集近似算子;给出了若干性质和定理的证明;通过与两个域上的粗糙集模型进行实例对比得出了两个域上的覆盖粗糙集模型的优点。     

一种基于特征点的三维网格盲水印算法

针对三维网格水印空域算法无法兼顾嵌入量与透明性,且水印盲检测过程繁琐的问题,提出一种基于特征点的盲水印算法。选取三维模型最远两点为全局特征点建立全局坐标系,根据仿射不变性原理将原始载体仿射到一个固定的球型空间,以增强对多种几何攻击的抵抗能力。根据载体点密集程度将其等分成若干个局部空间,以局部空间中离质心最远点为局部特征顶点建立局部几何坐标系,从而增强算法的透明性。利用顶点在坐标系的投影角度来存储水印索引,实现盲水印。实验结果表明,该算法能有效抵抗旋转、缩放、噪声等攻击,具有强鲁棒性和较好的不可感知性,同时兼具盲水印检测优势。     

Aggregation without Loss of Optimality in Competitive Location Models

In the context of competitive facility location problems demand points often have to be aggregated due to computational intractability. However, usually this spatial aggregation biases the value of the objective function and the optimality of the solution cannot be guaranteed for the original model. We present a preprocessing aggregation method to reduce the number of demand points which prevents this loss of information, and therefore avoids the possible loss of optimality. It is particularly effective in the frequent situation with a large number of demand points and a comparatively low number of potential facility sites, and coverage defined by spatial nearness. It is applicable to any spatial consumer behaviour model of covering type. This aggregation approach is applied in particular to a Competitive Maximal Covering Location Problem and to a recently developed von Stackelberg model. Some empirical results are presented, showing that the approach may be quite effective. This research was partially supported by the projects OZR1067 and SEJ2005-06273ECON.     

The local minima of the error surface of the 2-2-1 XOR network

All local minima of the error surface of the 2-2-1 XOR network are described. A local minimum is defined as a point such that all points in a neighbourhood have an error value greater than or equal to the error value in that point. It is proved that the error surface of the two-layer XOR network with two hidden units has a number of regions with local minima. These regions of local minima occur for combinations of the weights from the inputs to the hidden nodes such that one or both hidden nodes are saturated for at least two patterns. However, boundary points of these regions of local minima are saddle points. It will be concluded that from each finite point in weight space a strictly decreasing path exists to a point with error zero. This also explains why experiments using higher numerical precision find less “local minima”. This revised version was published online in June 2006 with corrections to the Cover Date.     

Averaging on Manifolds by Embedding Algorithm

We will propose a new algorithm for finding critical points of cost functions defined on a differential manifold. We will lift the initial cost function to a manifold that can be embedded in a Riemannian manifold (Euclidean space) and will construct a vector field defined on the ambient space whose restriction to the embedded manifold is the gradient vector field of the lifted cost function. The advantage of this method is that it allows us to do computations in Cartesian coordinates instead of using local coordinates and covariant derivatives on the initial manifold. We will exemplify the algorithm in the case of SO(3) averaging problems and will rediscover a few well known results that appear in literature.     

Class mean embedding for face recognition

Recently, local discriminant embedding (LDE) was proposed as a means of addressing manifold learning and pattern classification. In the LDE framework, the neighbor and class of data points are used to construct the graph embedding for classification problems. From a high dimensional to a low dimensional subspace, data points of the same class maintain their intrinsic neighbor relations, whereas neighboring data points of different classes no longer stick to one another. But, neighboring data points of different classes are not deemphasized efficiently by LDE and it may degrade the performance of classification. In this paper, we investigate its extension, called class mean embedding (CME), using class mean of data points to enhance its discriminant power in their mapping into a low dimensional space. After joined class mean data points, (1) CME may cause each class of data points to be more compact in the high dimension space; (2) CME may increase the quantity of data points, and solves the small sample size (SSS) problem; (3) CME may preserve well the local geometry of the data manifolds in the embedding space. Experimental results on ORL, Yale, AR, and FERET face databases show the effectiveness of the proposed method.