一种基于区域分割的表情鲁棒三维人脸识别方法

为了克服表情变化致使三维人脸识别性能不佳的问题,提出基于鼻尖点区域分割的表情鲁棒三维人脸识别方法。首先,根据表情对人脸影响具有区域性的特点,提出仅依赖鼻尖点的表情不变区域（刚性区域）和表情易变（非刚性区域）划分方法;然后针对表情不变区域和表情易变区域使用不同的特征描述方式并计算匹配相似度;最后将表情不变区域和表情易变的相似度进行加权融合实现最终身份识别。提出的方法分别在FRGC v2.0和自建WiseFace表情人脸数据库上达到98.52%和99.01%的rank 1识别率,证明该方法对表情变化具有较强的鲁棒性。     

基于光点阵列的三维表面数据获取技术及实现

现有的三维表面数据获取技术主要有光飞跃时间、激光扫描和结构光3种,均存在结构复杂、价格昂贵、不易使用的局限.基于光点阵列的三维数据获取完全不同于上述技术,其通过向待测物体表面投射二维光点阵列,用2个相机从不同角度获取图像,利用光点在2幅图像中的视差计算出其空间坐标.由于仅需要一次拍摄,因此可实现瞬时、动态的三维数据获取.该技术结合软件的自动配准和实时显示,可简化人工操作,实现三维测量的高速化、自动化和傻瓜化.     

CAD模型表面区域分割方法

三维模型表面区域分割技术在形状分析,尤其是局部形状分析中具有重要作用,传统的表面分割方法主要针对网格模型,而机械工程中的CAD模型通常用B-rep表达.提出一种B-rep形式的CAD模型表面区域分割方法,将模型表面划分为局部凸区域、凹区域和平区域的组合,并使得分割后的区域数量最少.为提高计算效率,提出一种二步法:首先在模型面的局部凸凹性分析的基础上,快速地将模型表面分割成初始的凸区域、凹区域和平区域;然后通过区域合并的方法对分割后的区域进行组合优化,得到一个最优的分割结果.实验结果证明,该方法能有效地分割模型的表面区域.     

三维激光扫描数据的压缩与地形采样

三维激光扫描测量具有速度快、效率高、实时性强等特点，由于其数据量特别大，数据特别精细，在存储和运算上受到的限制比较大。针对上述问题本文讨论了三维激光扫描数据的压缩和滤波，针对地形采集的需要，探讨了在三维激光扫描数据上获取地形采样点的具体方法。同时实例针对三维激光扫描数据点距小的特点对原有数据进行按序抽点，通过计算回光强度熵的信息对压缩效果进行检验，并用压缩后的数据生成等高线。     

三维扫描人体的点云数据精简技术

以三维扫描数据进行的人体重构,需要进行数据精简.传统的基于网格的精简方法需要记录网格之间的拓扑关系,因而空间和时间复杂度都很大.提出了一种不需要事先对扫描对象进行表面重构,而直接进行点云精简的方法.该方法无须对庞大数量的网格面片进行计算,无须记录网格的拓扑关系,而且能较好的保持被精简对象的原有特征,从而提高了点云精简的效率,减少了计算时间和存储空间.     

应用遗传模糊聚类实现点云数据区域分割

为了准确地实现点云数据的区域分割,将基于遗传算法的模糊聚类算法应用于逆向工程中的点云数据区域分割中。首先估算出法矢量、高斯曲率和平均曲率,并与坐标一起组成八维特征向量,用加权距离代替欧氏距离,然后通过遗传算法获得全局最优解的近似解;最后将近似解作为模糊聚类的初始解进行迭代,实现点云数据的区域分割,从而避免传统FCM算法的局部性和对初始解的敏感性,减少了迭代次数。以汽车钣金件为例,证明了应用遗传模糊聚类实现点云数据区域分割的有效性,并验证了该方法能快速、准确地实现点云数据的区域分割。     

网页区域分割与识别技术

结合HTML网页内部特征与外部的结构布局,提出采用映射表这种网页映射模式对网页视图进行变换,基于结构与启发式规则对网页进行区域分割与识别,从而准确得到具有网页各区域的内容.实验结果表明,此方法对各种复杂结构的网页区域分割与识别较为理想.     

三维激光扫描点云数据的空间压缩

三维激光扫描获得的点云数据,其数据量比较大。采用点云数据建立物体模型,存在模型分辨率的问题。模型的多分辨率表示是指对于同一模型,存在着由简到繁、由粗到精的集中表示。本文分析激光扫描数据的特点,基于其线扫描的特点,提出了扫描线斜率变化为准则实施数据压缩,其次对于密集数据又给出格网数据压缩方法。最后通过实例给出了压缩结果,并对压缩率和压缩效果作了比较分析。     

三维激光扫描系统的关键性技术研究

为获取三维数据信息及对所获得的三维数据信息进行处理,首先介绍了陕西科技大学计算机实验室三维激光扫描系统的组成及工作原理,对三维激光扫描系统的关键性技术如摄像机标定、影响测量精度因素、散乱数据点的消除以及点云数据的压缩问题的研究进行了概述,并指出该技术的应用在某些方面还需进一步完善和改进.     

3D object segmentation using B-Surface

3D object segmentation is important in computer vision such as target detection in biomedical image analysis. A new method, called B-Surface algorithm, is generated for 3D object segmentation. An improved 3D external force field combined with the normalized GVF is utilized. After the initialization of a surface model near the target, B-Surface starts to deform to locate the boundary of the object. First, it overcomes the difficulty that comes from analyzing 3D volume image slice by slice. And the speed of B-Surface deformation is enhanced since the internal forces are not needed to compute in every iteration deformation step. Next, the normal at every surface point can be calculated easily since B-Surface is a continuous deformable model. And it has the ability to achieve high compression ratio (ratio of data to parameters) by presenting the whole surface with only a relatively small number of control points. Experimental results and analysis are presented in this paper. We can see that the B-Surface algorithm can find the surface of the target efficiently.     

Exploration trees on highly complex scenes: A new approach for 3D segmentation

A new strategy for automatic object extraction in highly complex scenes is presented in this paper. The method proposed gives a solution for 3D segmentation avoiding most restrictions imposed in other techniques. Thus, our technique is applicable on unstructured 3D information (i.e. cloud of points), with a single view of the scene, scenes consisting of several objects where contact, occlusion and shadows are allowed, objects with uniform intensity/texture and without restrictions of shape, pose or location. In order to have a fast segmentation stopping criteria, the number of objects in the scene is taken as input. The method is based on a new distributed segmentation technique that explores the 3D data by establishing a set of suitable observation directions. For each exploration viewpoint, a strategy [3D data]-[2D projected data]-[2D segmentation]-[3D segmented data] is accomplished. It can be said that this strategy is different from current 3D segmentation strategies. This method has been successfully tested in our lab on a set of real complex scenes. The results of these experiments, conclusions and future improvements are also shown in the paper.     

针对医学重构模型的3D分割及压缩算法

提供便捷的交互手段,从3D重构模型中精确分割感兴趣区域,为医生术前手术规划提供更为直观和准确的诊断信息。利用VTK（Visualization ToolKit）开发包构架系统平台,采用3D区域生长法分割感兴趣部位,结合数学形态法消除数据的病态关联,实现精确分割,进一步修改数据掩模完成分割后数据的压缩存储。实验证明了上述算法的有效性,可得到良好的3D分割效果。     

Taiwanese adult foot shape classification using 3D scanning data

This study classifies the foot shapes of Taiwanese using 3D foot scanning data from 2000 males and 1000 females. Nine foot dimensions relative to foot length and absolute measures in the common foot length categories were applied to compare the gender differences. Using foot breadth in % foot length (% FL), ball of foot length in % FL and arch height in % FL as feature parameters, three foot shape types for males and females can be classified. Significant gender differences were found in seven of the nine foot dimensions. Females had greater ball of foot length than males (0.2% FL). When comparing feet of the same foot length, males had greater breadth, girth and height dimensions than females, except for toe height. In addition, ethnic differences in foot shape were also observed. The findings can provide very useful information for building gender-specific shoe lasts and designing footwear insoles.     

基于面结构光的机械工件三维扫描系统设计

针对工业机器人对自动化装配过程生产效率的提高以及工件拾取对三维扫描技术的应用需求,设计了能够准确提取机械工件表面点云的视觉系统。扫描系统主要由计算机、投影仪和工业相机构成。基于光学测量和机器视觉的原理,主要研究设计了扫描系统工业相机和投影仪的标定策略、结构光栅编码解码的检测策略以及点云重构的几何策略。对于机械工件三维扫描重构的多余背景平面点云,研究设计了通过随机选取点云并反复迭代构造背景平面实现分割的有效方法。实验结果表明采用面结构光技术,由投影仪投影不同频率的结构光栅在机械工件上,工业相机同步采集被机械工件调制的结构光栅图像,对图像中的光栅条纹进行提取并计算,并利用三角检测算法提取机械工件表面点云的方案具有高准确性,能够有效重构机械工件表面点云。     

Providing real-estate services through the integration of 3D laser scanning and building information modelling

There is an opportunity for real-estate services sector to deliver more accurate, faster and quality building surveys and information models. This paper reports on a study, designed to establish automated procedures for the development of a digital model to assist in faster and better services and delivery of real-estate services by integrating 3D laser scanning and BIM technology. It proposes an intuitive and interactive building model that is easy to query and navigate, and thus support property developers, buyers and sellers in the property sales sector. An outline of the new approach is provided to illustrate the benefits of the proposed method to the real-estate services sector. The key arguments in the paper are consolidated by the results of a qualitative study amongst real-estate professionals, which sought to determine the added value of BIM-3D laser scanning in comparison to conventional building surveying and Computer Aided Design (CAD) methods.     

A two-stage fuzzy multi-objective framework for segmentation of 3D MRI brain image data

Segmentation of Magnetic Resonance Imaging (MRI) brain image data has a significant impact on the computer guided medical image diagnosis and analysis. However, due to limitation of image acquisition devices and other related factors, MRI images are severely affected by the noise and inhomogeneity artefacts which lead to blurry edges in the intersection of the intra-organ soft tissue regions, making the segmentation process more difficult and challenging. This paper presents a novel two-stage fuzzy multi-objective framework (2sFMoF) for segmenting 3D MRI brain image data. In the first stage, a 3D spatial fuzzy c-means (3DSpFCM) algorithm is introduced by incorporating the 3D spatial neighbourhood information of the volume data to define a new local membership function along with the global membership function for each voxel. In particular, the membership functions actually define the underlying relationship between the voxels of a close cubic neighbourhood and image data in 3D image space. The cluster prototypes thus obtained are fed into a 3D modified fuzzy c-means (3DMFCM) algorithm, which further incorporates local voxel information to generate the final prototypes. The proposed framework addresses the shortcomings of the traditional FCM algorithm, which is highly sensitive to noise and may stuck into a local minima. The method is validated on a synthetic image volume and several simulated and in-vivo 3D MRI brain image volumes and found to be effective even in noisy data. The empirical results show the supremacy of the proposed method over the other FCM based algorithms and other related methods devised in the recent past.     

优化的PCNN自适应三维图像分割算法*

脉冲耦合神经网络(pulse coupled neural network,PCNN)对图像分割具有天然的优势,但是传统的PCNN模型参数难以确定,且算法耗时多。对多种PCNN模型进行研究改进,并利用统计学知识提出了一种精简高效的自适应三维分割算法。将其用于脑部磁共振成像(magnetic resonance imaging,MRI)图像的分割,把脑组织分成白质、灰质和脑脊液。与标准PCNN、传统的Otsu阈值方法、SPM8工具箱及专家手动分割结果的对比实验表明,该自适应算法具有精确性、高效性。