基于照片的人脸建模

研究由一张正面照片和一张侧面照片合成头部三维模型的方法.从照片中提取面部特征点后.得到人脸在两个坐标系统中的三维空间数据坐标,从两张照片可以合成任意角度视图.然后进行数据拟合得到非特征点的数据,最后根据三维数据重建得到三维人脸模型.     

一种基于反射特性的人脸三维重建方法

不同姿势下的人脸识别研究中的一种重要思路就是在三维空间解决姿势变化问题,如何由二维人脸图像得到三维人脸形状是其中的一项关键技术.本文提出了一种由两幅正面人脸图像估计人脸表面反射特性,重建三维形状的算法.首先根据人脸的对称特性,由两幅给定光照的正面人脸图像,估计得到个性化人脸特征:反射特性(反射系数与法向量的乘积),并提出消除鼻梁阴影的改进算法;然后由反射特性重建三维人脸形状,最后根据估计得到的反射特性和三维形状合成不同姿势下的人脸图像,实验结果表明,本文提出算法合成的人脸图像更自然一些,而且合成图像不受训练集图像的影响.本方法计算简单,并且不需要任何三维人脸数据作为先验知识.     

基于体绘制思维的人脸识别算法优化研究

传统的人脸识别算法主要解决二维正面图像识别,如果人体姿态发生明显变化,或外界环境发生显著变化,则算法性能大大降低,无法获取准确的识别结果。体绘制算法针对三维数据场进行绘制,绘制的图像能够描述人脸的内部细节,可提高人脸识别精度。因此,提出一种基于体绘制思维的人脸识别算法,依据聚类思想对二维人脸库进行聚类,在各分类的基础上,构建人脸相似模型。通过错切变形体制算法,构建人脸体数据,实现人脸体数据坐标系统的转换以及人脸三维图像的合成,从人脸三维图像中采集人脸特征,利用相似性模型对人脸关键特征同数据库已有的特征进行匹配分析,完成人脸身份识别。实验结果说明,所提算法对于不同表情和不同光照条件下的人脸图像,都具有较高的识别率和鲁棒性。     

双目下点云的三维人脸重建

提出一种在双目视觉系统下进行人脸重建的方法。首先,通过双目系统拍摄人脸的左右图像;其次,用Grab-Cut的方法的把人脸图像分割出来从而降低立体匹配的搜索范围;然后,用区域匹配算法得到人脸的视差图,从而得到人脸的三维点云;最后对不同角度的人脸图像进行SIFT特征提取和匹配。将提取的SIFT特征点和匹配关系反射到三维点云数据,获取不同角度人脸的三维点云数据的特征点和匹配关系,完成对不同角度的人脸进行粗配准。     

基于人脸面部特征的三维人脸预处理方法

基于自动检测人脸特征点坐标,利用人脸水平对称的性质,提出一种新的三维人脸姿态预处理方法。首先基于人脸特征点坐标和人脸几何特性,确定人脸本征平面,实现人脸姿态归一化,然后对归一化的人脸点云数据提取面部数据点,最后对提取到的面部数据点去奇异点、中值滤波以及补洞。最后在FRGCv2.03D人脸数据库进行实验,验证了提出的三维人脸数据预处理方法,并取得了理想结果。     

基于激光扫描的人脸图像模糊纹理特征提取方法

由于图像的高频细节信息较为复杂，在人脸图像识别中特征提取准确度严重下降，为此，提出一种基于激光扫描的人脸图像模糊纹理特征提取方法。通过直接标定的方式获取相机采样图片中标定点坐标和世界坐标系之间的关系，使用相机拍摄标准色板图像，标定感光曲线，通过激光扫描得到人脸图像。将获取的人脸图像预处理，将预处理之后得到的人脸图像特征实行CCS-LBP编码处理，将编码处理得到的图像特征融合处理，获取一个全新的纹理特征，最终达到人脸图像模糊纹理特征提取的目的。实验结果表明，所提方法可以有效提升特征提取结果准确性。     

多视图三维人脸重建方法综述

<正>在现实生活中，人脸蕴含了个体丰富的信息，在视觉感知中占有非常重要的地位，因此人脸在三维重建中是一个非常重要的对象，具有广泛的应用前景。三维人脸重建具有很高的研究价值和意义。目前有关三维人脸重建的研究大多是针对单张人脸图像，虽然单视图三维人脸重建已经在人脸识别、虚拟现实等领域有了广泛应用，但是它仍然存在很大弊端，比如单张图像重建出的模型准确性和精度不足，但是多张图像却可以提供更多的观测数据，从而可以提高人脸三维模型的精度和准确性。     

基于三维变换的多姿态人脸识别

现有的人脸识别系统大多基于数码相机等设备获取的二维人脸图像,当目标的姿态或者摄像机的方位发生改变时,往往会造成图像的变形以至于无法识别。而当输入的人脸为三维图像时,可以进行任意的姿态变换,从而实现对目标的识别。因此,可以通过三维人脸重建并进行空间姿态变换的方法实现任意姿态的人脸识别。在对原有三维人脸识别算法研究的基础上提出了更为通用的方法,该方法将三维深度数据与二维RGB数据结合起来,通过空间变换实现同一人脸的多姿态表示,从而建立人脸库,而在测试时只需要输入普通二维图像即可实现人脸识别。实验结果表明,此方法在采集的人脸库上,得到了很好的识别效果。     

基于改进型深度数据流形的数据分类算法及在人脸中的应用

针对数据分类问题的局限,提出一种基于改进型深度数据流形的数据分类算法并将其应用到人脸识别中。首先,通过采集人脸图像的深度信息,利用稀疏表示对其进行去噪处理;再结合图像的颜色信息,重新生成三维人脸信息数据库,通过对人脸数据的流形分析得到最优的降维结果,按十字十乘交叉验证法的原则选取训练集和测试集,将训练集输入支持向量机算法建立数据分类器;最后,将测试集输入训练完成的分类器中,实现人脸数据分类。选取ORL,Yale两类人脸图像标准数据库与传统人脸识别算法进行交叉对比实验,验证算法的优越性和可行性。实验结果表明：所提出的算法有较高的分类准确率,可有效地完成人脸识别。     

基于单视图的多姿态人脸图像生成技术研究

该文提出了一种基于单视图或小样本的多姿态人脸图像生成技术,它首先利用一个特征点集表示人脸,然后基于二元高次多项式函数最小二乘方法对人脸各姿态之间的特征点集坐标变化进行拟合,形成全局的变形域,最后由单视图通过变形映射生成多姿态人脸图像。实验结果表明,利用单视图和生成的多姿态图像进行多姿态人脸识别,正确率得到大大提高,证明该文人脸图像生成技术十分有效。     

Model-based analysis synthesis image coding (MBASIC) system for a person's face

The initial conception of a model-based analysis synthesis image coding (MBASIC) system is described and a construction method for a three-dimensional (3-D) facial model that includes synthesis methods for facial expressions is presented. The proposed MBASIC system is an image coding method that utilizes a 3-D model of the object which is to be reproduced. An input image is first analyzed and an output image using the 3-D model is then synthesized. A very low bit rate image transmission can be realized because the encoder sends only the required analysis parameters. Output images can be reconstructed without the noise corruption that reduces naturalness because the decoder synthesizes images from a similar 3-D model.

In order to construct a 3-D model of a person's face, a method is developed which uses a 3-D wire frame face model. A full-face image is then projected onto this wire frame model. For the synthesis of facial expressions two different methods are proposed; a clip-and-paste method and a facial structure deformation method.     

Model-based image coding advanced video coding techniques for verylow bit-rate applications

The paper gives an overview of model-based approaches applied to image coding, by looking at image source models. In these model-based schemes, which are different from the various conventional waveform coding methods, the 3-D properties of the scenes are taken into consideration. They can achieve very low bit rate image transmission. The 2-D model and 3-D model based approaches are explained. Among them, a 3-D model based method using a 3-D facial model and a 2-D model based method utilizing 2-D deformable triangular patches are described. Works related to 3-D model-based coding of facial images and some of the remaining problems are also described     

Geometry-assisted image-based rendering for facial analysis and synthesis

In this paper, we present an image-based method for the tracking and rendering of faces. We use the algorithm in an immersive video conferencing system where multiple participants are placed in a common virtual room. This requires viewpoint modification of dynamic objects. Since hair and uncovered areas are difficult to model by pure 3-D geometry-based warping, we add image-based rendering techniques to the system. By interpolating novel views from a 3-D image volume, natural looking results can be achieved. The image-based component is embedded into a geometry-based approach in order to limit the number of images that have to be stored initially for interpolation. Also temporally changing facial features are warped using the approximate geometry information. Both geometry and image cube data are jointly exploited in facial expression analysis and synthesis.     

基于双目立体视觉测量原理的物体运动速度测量

采用双目立体视觉测量系统进行炮弹速度的测量, 实现一种利用无速度测量因素测量设备测速的新方法。选择合适参数的两 台摄像机获得被测物体清晰的像,将两台摄像机搭建成光轴平行的双目视觉测量 系统,获得炮弹在运行过程中的每一时刻的三维轮廓数据,根据获得的三维数据进 行空间位置节点的三维插值,得到炮弹在t时间段内运行的距离,并求取平均 速度。仿真实验结果表明,本文方法可以准确、快速利用无速度测量因素的测量 设备获得炮弹的运行速度。     

Ray phase space approach for 3-D imaging and 3-D optical data representation

We propose a framework to model, analyze and design three-dimensional (3-D) imaging systems. A system engineering approach is adopted which relates 3-D images (real or synthesized) to 3-D objects (real or synthesized) using a novel representation of the optical data which we call "ray phase space". The framework provides a powerful tool for determining the performance of 3-D imaging systems, for generating computational reconstruction of 3-D images and for optimizing 3-D imaging systems.     

A Method for Head—shoulder Segmentation and Human Facial Feature Positioning

ＡＭｅｔｈｏｄｆｏｒＨｅａｄｓｈｏｕｌｄｅｒＳｅｇｍｅｎｔａｔｉｏｎａｎｄＨｕｍａｎＦａｃｉａｌＦｅａｔｕｒｅＰｏｓｉｔｉｏｎｉｎｇＨｕＴｉａｎｊｉａｎＣａｉＤｅｊｕｎＤｅｐａｒｔｍｅｎｔｏｆＥｌｅｃｔｒｉｃａｌａｎｄＩｎｆｏｒｍａｔｉｏｎＥｎｇｉ...     

Three-dimensional myocardial strain reconstruction from tagged MRI using a cylindrical B-spline model

In this paper, we present a new method for reconstructing three-dimensional (3-D) left ventricular myocardial strain from tagged magnetic resonance (MR) image data with a 3-D B-spline deformation model. The B-spline model is based on a cylindrical coordinate system that more closely fits the morphology of the myocardium than previously proposed Cartesian B-spline models and does not require explicit regularization. Our reconstruction method first fits a spatial coordinate B-spline displacement field to the tag line data. This displacement field maps each tag line point in the deformed myocardium back to its reference position (end-diastole). The spatial coordinate displacement field is then converted to material coordinates with another B-spline fit. Finally, strain is computed by analytically differentiating the material coordinate B-spline displacement field with respect to space. We tested our method with strains reconstructed from an analytically defined mathematical left ventricular deformation model and ten human imaging studies. Our results demonstrate that a quadratic cylindrical B-spline with a fixed number of control points can accurately fit a physiologically realistic range of deformations. The average 3-D reconstruction computation time is 20 seconds per time frame on a 450 MHz Sun Ultra80 workstation.     

Face analysis and synthesis

The author's goal is to generate a virtual space close to the real communication environment between network users or between humans and machines. There should be an avatar in cyberspace that projects the features of each user with a realistic texture-mapped face to generate facial expression and action controlled by a multimodal input signal. Users can also get a view in cyberspace through the avatar's eyes, so they can communicate with each other by gaze crossing. The face fitting tool from multi-view camera images is introduced to make a realistic three-dimensional (3-D) face model with texture and geometry very close to the original. This fitting tool is a GUI-based system using easy mouse operation to pick up each feature point on a face contour and the face parts, which can enable easy construction of a 3-D personal face model. When an avatar is speaking, the voice signal is essential in determining the mouth shape feature. Therefore, a real-time mouth shape control mechanism is proposed by using a neural network to convert speech parameters to lip shape parameters. This neural network can realize an interpolation between specific mouth shapes given as learning data. The emotional factor can sometimes be captured by speech parameters. This media conversion mechanism is described. For dynamic modeling of facial expression, a muscle structure constraint is introduced for making a facial expression naturally with few parameters. We also tried to obtain muscle parameters automatically from a local motion vector on the face calculated by the optical flow in a video sequence     

三维观测模型下蒸发波导时空态势压缩感知

为减小蒸发波导时空态势感知过程中采集存储的数据量和计算量,将现有一维压缩感知观测模型推广,得到三维观测模型,并改进得到三维观测下的盲稀疏回溯重构算法.通过一个等效三维感知矩阵对时间维和空间二维进行同时观测,并考察其整体重构.新方法维护了蒸发波导参数内在的相关性,缓解了单独按时间维或空间维感知引入的重构人为效应.理论分析和实验表明,在相同压缩比下,时空三维感知结果最接近真值.     

信号频率和2-D到达方向分离估计方法

本文基本三个阵列空间的排列组合提出了一种新的多个空间信号频率和2－D到达方向的估计方法。由于该方法是将问题转化为三个1－D问题且在每一维利用计算有效的ESPRIT算法和利用子阵列的输出数据矩阵具有相同的列空间，因此避免了多维谱估计中的谱峰搜索和参数间的配对。计算机模拟实验证实了其有效性。