三维限定Voronoi网格剖分细化算法

针对分段线性复合形约束条件下的三维限定Voronoi剖分问题,提出一种细化算法.首先证明了分段线性复合形中的元素在最终生成的三维限定Voronoi网格中可表示为Power图结构;受此启发,提出了对限定线段平面片分别进行一维二维Power图细化以实现三维限定Voronoi 网格生成的细化算法,并且证明了该算法对于任意分段线性复合形收敛.最后通过实例验证了文中算法的有效性.     

基于肤色学习的多人脸前景抽取方法

针对多人脸场景下快速准确提取人脸内容的问题,提出了基于肤色学习的多人脸前景抽取方法。首先,给出了基于肤色学习的肤色前景分割模型。根据肤色专家的论文结果,采集了著名的SPA数据库的1 200张人脸进行肤色抽样,建立学习模型以得到每个人种在颜色空间的肤色参数,据此进行肤色图像分割,得到肤色前景。其次,利用人脸特征点学习算法,以常见人脸68个特征点为目标,结合肤色前景信息分割出人脸种子区域;并计算人脸中心点,来构建人脸椭圆边界模型以及确定遗传范围。最后,建立了有效抽取算法,在人脸椭圆边界内利用遗传机制进行人脸再生,从而抽取得到有效人脸区域。以三类不同数据库为基础,收集了100张有代表性的多人脸图像,实验结果表明所提方法对这些图像的多人脸抽取的结果准确率达到98.4%以上,且该方法对中密度人群的人脸内容抽取有显著效果,并为人脸识别算法的准确性和可用性提供了基础。     

基于聚类的人脸图像检索及相关反馈

提出了一种基于聚类的人脸图像检索算法. 首先利用归一化分割(Normalized cuts, NCuts)在每个时间段内分别对人脸聚类, 使同一个人在不同情况下的人脸图像聚为一类. 其次采用连续AdaBoost算法学习得到的人脸识别分类器度量人脸之间的相似度, 并进一步提出查询人脸与人脸聚类之间的相似度用于检索. 为了进一步提高性能, 用户可以在线标定错检和漏检的结果, 相关反馈环节把用户的交互标定结果作为约束条件重新对人脸聚类. 本文把人脸图像检索算法应用于自动的检索系统中, 在包含超过一千张人脸图像的家庭数码相册上, 通过与其他方法的对比实验证明了基于聚类的人脸图像检索算法是有效的.     

Missing sets in rational parametrizations of surfaces of revolution

Parametric representations do not cover, in general, the whole geometric object that they parametrize. This can be a problem in practical applications. In this paper we analyze the question for surfaces of revolution generated by real rational profile curves, and we describe a simple small superset of the real zone of the surface not covered by the parametrization. This superset consists, in the worst case, of the union of a circle and the mirror curve of the profile curve.     

智能配镜三维特征参数提取方法研究

摘 要：针对智能配镜中三维面部特征点提取算法复杂度较高的问题,提出一种将三维点 云转换为映射图像定位特征点的方法。采用 Voronoi 方法计算面部三角网格各顶点处的高斯曲 率、平均曲率。选取鼻尖、眼角等曲率特征明显的区域估计面部点云姿态。根据曲率旋转不变 性,使用初选的点云方向向量简化旋转矩阵的计算,使面部点云正面朝向视点。将点云映射转 换为图像,三维网格模型中三角面片一对一映射到图像中的三角形。搭建卷积神经网络,使用 Texas 3DFRD 数据集进行模型训练。进行人脸对齐,预测所得各面部特征点分别限制在图像某 三角形中。根据图像中三角形映射查找三维网格模型中对应三角面片,通过三角面片顶点坐标 计算配镜所需的面部特征点位置坐标,实现配镜特征参数的提取。     

边界面法数值结果的云图表征

边界面法继承了传统边界元法的优点,并将几何实体的边界曲面离散为参数空间里的曲面单元,在处理一些特殊问题如移动边界、高梯度、大变形等方面显示出特殊的优越性。但是也使得计算结果的后处理遇到困难。提出了一种基于黎曼度量推进波前法生成三角背景网格的实用边界面法计算结果后处理方法。该法对求解域剖分成三角背景网格然后将计算结果映射到网格节点上,通过区域填充获得计算结果的云图。温度场的数值算例表明该方法可靠实用。     

基于Delaunay四面体剖分的网格分割算法

为了构建有意义曲面分片,提出一种基于Delaunay四面体剖分的网格分割算法.首先根据Delaunay四面体剖分得到多边形网格内部的四面体,求出每个面上反映网格内部信息的Delaunay体距离;然后对Delaunay体距离进行平滑处理,再对网格上面的Delaunay体距离进行聚类,用高斯混合模型对Delaunay体距离作柱状图的拟合,利用期望最大化算法来快速求得拟合结果;最后结合图切分技术,同时考虑聚类的结果、分割区域的边界平滑和视觉认知中的最小规则,得到最终的网格分割结果.实验结果表明,采用文中算法可以有效地实现有意义的网格分割.     

分区变形与多尺度约束结合的3D面皮点对应

针对准确建立3D面皮间点对应关系这一难题, 引入积分不变量的多尺度约束, 提出了分区变形与多尺度约束结合的3D面皮点对应方法。首先对待对应面皮和参考面皮进行法兰克福坐标矫正和特征点的标定。然后在对面皮完成测地线分区的基础上, 对各分区进行径向基函数变形, 使两个面皮的相应分区近似重合。最后在参考面皮上选取待对应点, 根据重合的面皮分区间局部相对位置的稳定性, 在待对应面皮上建立待对应点的候选集, 利用体积积分不变量的多尺度约束选定最佳对应点, 进而实现了3D面皮的点对应。实验表明, 算法有效提高了点对应的准确度。     

面向自然景观的环境艺术设计教育理念研究

本文分析了环境艺术设计在我国的发展概况和发展方向,结合当前对自然景观的日益重视和相关人才匮乏这一现实,提出了面向自然的环境艺术设计的教育理念,强调其核心理念是遵循生态系统运行规律和保护生态系统的美学价值。这种理念是面向生态文明建设的设计理念,体现了建设资源节约型、环境友好型社会的时代要求,是对那种反映物欲主义奢华设计观念的批判。面向自然的环境艺术设计通过现代设计的方法保护和合理利用自然景观,改善人类的生存状况,追求理想的生活境界,具有极强的现实意义。     

基于近红外与可见光双目视觉的活体人脸检测方法

针对人脸识别系统易受伪造攻击的问题,提出了一种基于近红外与可见光双目视觉的活体人脸检测方法。首先,采用近红外与可见光双目装置同步获取人脸图像,提取两图像的人脸特征点,利用双目关系实现特征点的匹配并获取其深度信息,再利用深度信息进行三维点云重建;然后,将全部人脸特征点划分为四个区域,计算各区域内人脸特征点在深度方向的平均方差;接着,选取人脸关键特征点,以鼻尖点为参照点,计算鼻尖点到人脸关键特征点之间的空间距离;最后,利用人脸特征点的深度值方差和空间距离来构造特征向量,使用支持向量机（SVM）实现活体人脸判断。实验结果表明,所提方法能够准确检测活体人脸以及有效抵御伪造人脸的攻击,在实验测试中达到99.0%的识别率,在准确性和鲁棒性上优于利用人脸特征点深度信息进行检测的同类算法。     

基于肤色特征的人脸检测技术研究

文章提出一种多人脸图像中人脸检测与定位方法,将图像从RGB色彩空间转换到YCrCb色彩空间中,根据肤色点在CrCb空间中的分布情况进行肤色点检测,并滤除肤色检测后的孤立噪声,利用势函数方法获得人脸候选区域。然后,根据人脸的结构特征对候选区域进行人脸区域的判别和定位,最终实现图像中多人脸的检测功能,并通过仿真实验证明了该方法的有效性。     

Partitioning polyhedral objects into nonintersecting parts

An algorithm is described for partitioning intersecting polyhedrons into disjoint pieces and, more generally, removing intersections from sets of planar polygons embedded in three space. Polygons, or faces, need not be convex and may contain multiple holes. Intersections are removed by considering pairs of faces and slicing the faces apart along their regions of intersection. To reduce the number of face pairs examined, bounding boxes around groups of faces are checked for overlap. The intersection algorithm also computes set-theoretic operations on polyhedrons. Information gathered during face cutting is used to determine which portions of the original boundaries may be present in the result of an intersection, a union, or a difference of solids. The method includes provisions to detect and in some cases overcome, the effects of numerical inaccuracy on the topological decisions that the algorithm must make. The regions in which ambiguous results are possible are flagged so that the user can take appropriate action     

Accurate and energy-efficient boundary detection of continuous objects in duty-cycled wireless sensor networks

With the development and wide adoption of industrial wireless sensor networks to support various domain applications, the boundary detection of continuous objects has become an important research challenge, where improving the accuracy of boundary area while reducing the energy consumption are the first-class citizens to be considered. To address this research challenge, this article proposes a two-stage boundary face detection mechanism, where sensor nodes are duty-cycled and to be deployed in a dense fashion. When the occurrence of potential events are recognized using the initially activated sensor nodes, the boundary faces of continuous objects are constructed through adopting planarization algorithms. Thereafter, sensor nodes contained in certain boundary faces are examined, where their sensory data are estimated using spatial interpolation methods. Certain sensor nodes are selected to be woken up, only when their sensory data suggest that they should be more appropriate candidates of boundary sensor nodes. Consequently, the size of boundary faces is reduced, and this coarse-to-fine refinement procedure iterates, until all sensor nodes contained in the boundary faces have been examined. Experimental evaluation result shows that the boundary area can be refined significantly and be more precise, where the half of the initial boundary face area should be reduced in most situations.     

Boolean Operations on n-Dimensional Objects

Computation of the union, intersection, and difference of n-dimensional objects plays a central role in several computer-aided geometric design problems. An algorithm for computing these operations that uses a boundary classification technique is presented here. The algorithm is recursive in structure, with the recursion being on the dimensions of objects dealt with at each stage. The representation treats all entities as objects, making no distinction between faces, edges, or vertices. The objects produced are "regularized"; that is, there are no degenerate boundaries such as dangling edges. The sample application given involves hidden-surface removal.     

人脸样貌独立判别的协作表情识别算法

为了降低样貌、姿态、眼镜以及表情定义不统一等因素对人脸表情识别的影响,提出一种人脸样貌独立判别的协作表情识别算法。首先,采用自动的人脸检测算法定位、对齐视频每帧的人脸区域,并从人脸视频序列中选择峰值表情的人脸;然后,采用峰值人脸与某个表情类内的所有人脸产生表情类内差异人脸信息,并通过计算峰值表情人脸与表情类内差异人脸的差异信息获得协作的表情表示;最终,采用基于稀疏的分类器与表情表示决定每个人脸表情的标签。采用欧美与亚洲人脸的数据库进行仿真实验,结果表明本算法获得了较好的表情识别准确率,对不同样貌、佩戴眼镜的人脸样本也具有较好的识别效果。     

Probing a scene of nonconvex polyhedra

We show, in this paper, how the exact shapes of a class of polyhedral scenes can be computed by means of a simple sensory device issuing probes. A scene in this class consists of disjoint polyhedra with no collinear edges, no coplanar faces, and such that no edge is contained in the supporting plane of a nonincident face. The basic step of our method is a strategy for probing a single simple polygon with no collinear edges. When each probe outcome consists of a contact point and the normal to the object at the point, we present a strategy that allows us to compute the exact shape of a simple polygon with no collinear edges by means of at most3n — 3 probes, wheren is the number of edges of the polygon. This is optimal in the worst case. This strategy can be extended to probe a family of disjoint polygons. It can also be applied in planar sections of a scene of polyhedra of the class above to find out, in turn, each edge of the scene. If the scene consists ofk polyhedra with altogethern faces andm edges, we show that \(\tfrac{{10}}{3}n\left( {m + k} \right) - 2m - 3k\) probes are sufficient to compute the exact shapes of the polyhedra.     

Exploiting Voronoi diagram properties in face segmentation and feature extraction

Segmentation of human faces from still images is a research field of rapidly increasing interest. Although the field encounters several challenges, this paper seeks to present a novel face segmentation and facial feature extraction algorithm for gray intensity images (each containing a single face object). Face location and extraction must first be performed to obtain the approximate, if not exact, representation of a given face in an image. The proposed approach is based on the Voronoi diagram (VD), a well-known technique in computational geometry, which generates clusters of intensity values using information from the vertices of the external boundary of Delaunay triangulation (DT). In this way, it is possible to produce segmented image regions. A greedy search algorithm looks for a particular face candidate by focusing its action in elliptical-like regions. VD is presently employed in many fields, but researchers primarily focus on its use in skeletonization and for generating Euclidean distances; this work exploits the triangulations (i.e., Delaunay) generated by the VD for use in this field. A distance transformation is applied to segment face features. We used the BioID face database to test our algorithm. We obtained promising results: 95.14% of faces were correctly segmented; 90.2% of eyes were detected and a 98.03% detection rate was obtained for mouth and nose.     

Kernel machine-based one-parameter regularized fisher discriminant method for face recognition.

This paper addresses two problems in linear discriminant analysis (LDA) of face recognition. The first one is the problem of recognition of human faces under pose and illumination variations. It is well known that the distribution of face images with different pose, illumination, and face expression is complex and nonlinear. The traditional linear methods, such as LDA, will not give a satisfactory performance. The second problem is the small sample size (S3) problem. This problem occurs when the number of training samples is smaller than the dimensionality of feature vector. In turn, the within-class scatter matrix will become singular. To overcome these limitations, this paper proposes a new kernel machine-based one-parameter regularized Fisher discriminant (K1PRFD) technique. K1PRFD is developed based on our previously developed one-parameter regularized discriminant analysis method and the well-known kernel approach. Therefore, K1PRFD consists of two parameters, namely the regularization parameter and kernel parameter. This paper further proposes a new method to determine the optimal kernel parameter in RBF kernel and regularized parameter in within-class scatter matrix simultaneously based on the conjugate gradient method. Three databases, namely FERET, Yale Group B, and CMU PIE, are selected for evaluation. The results are encouraging. Comparing with the existing LDA-based methods, the proposed method gives superior results.     

关键点匹配三维人脸识别方法*

提出了一种新颖的三维人脸识别算法,其基本思路是,把代表人脸的三维点云沿X、Y或Z轴旋转,反复多次把3D人脸关键点投影到2.5D图像上,然后提取2.5D图像的关键点并进行标记,而用这些比原来小得多的关键点代替原来的面扫描。面对未知的待测人脸首先通过执行相同的多视角特征点提取技术提取关键点,然后应用一个新的加权特征点匹配算法进行识别。通过用GavabDB三维面部识别数据集进行试验评估,这个方法对中性表情人脸可获得高达94％的识别精度,对人脸表情辨识（如微笑）的准确率也超过了88％。实验结果表明,此方法在识别精     

Preserving privacy by de-identifying face images

In the context of sharing video surveillance data, a significant threat to privacy is face recognition software, which can automatically identify known people, such as from a database of drivers' license photos, and thereby track people regardless of suspicion. This paper introduces an algorithm to protect the privacy of individuals in video surveillance data by deidentifying faces such that many facial characteristics remain but the face cannot be reliably recognized. A trivial solution to deidentifying faces involves blacking out each face. This thwarts any possible face recognition, but because all facial details are obscured, the result is of limited use. Many ad hoc attempts, such as covering eyes, fail to thwart face recognition because of the robustness of face recognition methods. This work presents a new privacy-enabling algorithm, named k-Same, that guarantees face recognition software cannot reliably recognize deidentified faces, even though many facial details are preserved. The algorithm determines similarity between faces based on a distance metric and creates new faces by averaging image components, which may be the original image pixels (k-Same-Pixel) or eigenvectors (k-Same-Eigen). Results are presented on a standard collection of real face images with varying k.