一种无标记点人脸表情捕捉与重现算法

提出了一种无标记点的人脸表情捕捉方法.首先根据ASM（Active Shape Model）人脸特征点生成了覆盖人脸85%面部特征的人脸均匀网格模型;其次,基于此人脸模型提出了一种表情捕捉方法,使用光流跟踪特征点的位移变化并辅以粒子滤波稳定其跟踪结果,以特征点的位移变化驱动网格整体变化,作为网格跟踪的初始值,使用网格的形变算法作为网格的驱动方式.最后,以捕捉到的表情变化数据驱动不同的人脸模型,根据模型的维数不同使用不同的驱动方法来实现表情动画重现,实验结果表明,提出的算法能很好地捕捉人脸表情,将捕捉到的表情映射到二维卡通人脸和三维虚拟人脸模型都能取得较好的动画效果.     

多表情人脸肖像的自动生成

肖像是一种能够抓住人物特征,又能隐藏细节,保留个人隐私的艺术表现形式,本文提出一种以中性表情人脸作为输入,自动生成不同表情的肖像算法.首先利用主动形状模型(Active Shape Model,ASM)提取人脸的关键特征点,然后根据统计学习获取的不同表情人脸的FAP(Facial Animation Parameter)规则,对中性人脸的特征点进行变形,生成表情三角网格,将中性人脸图像作为纹理映射到表情人脸网格,生成表情人脸图像,最后利用图像的梯度域信息和非真实感渲染技术,将带表情的人脸生成具有肖像风格的人脸图像.所生成的多表情人脸肖像效果良好,能够应用于网络和报刊杂志等非真实感图形学和数字娱乐等领域中.     

人脸面部表情的动画算法研究

利用计算机进行人脸造型、建立人脸表情动画以及对人脸肖像进行夸张处理是当前的一项热门研究课题,其技术和产品有着广阔的应用前景和巨大的经济效益。文中研究了人脸表情特征,选择一种合适的人脸表情动画和人脸变形技术的方法,并将二者结合在一起,设计了一个可以实现人脸卡通动画效果的系统。     

面部表情跟踪描绘中的边缘特征量

由于外界环境的不确定性和人脸的复杂性,人脸表情的跟踪与计算机形象描绘是一个较难问题.基于此问题,提出了一种有别于模式识别、样本学习等传统手段的较为简单解决方法,在视频采集条件下,分析帧图像,通过对比多种边缘检测方法,采用一种基于边缘特征提取的人脸表情建模方法,来完成用于表情描绘的面部特征量提取与建模,并结合曲线拟合和模型控制等手段,进行人脸卡通造型生成和二维表情动画模拟.实现了从输入数据生成卡通造型画并真实地表现出表情变化情况.     

一种基于三维扫描数据的人脸建模方法

三维扫描仪可以准确获取人脸的几何形状与纹理,但原始的人脸扫描数据仅为一张连续曲面,不符合实际的人脸结构,无法用于人脸动画。针对此问题,提出了一种由三雏扫描数据进行人脸建模的方法,将一个具备完整结构的通用人脸模型与扫描数据进行初步适配,再采用细节重建技术恢复特定人脸的表面细节和皮肤纹理。实验表明,该方法建立的三维人脸模型真实感强,结构完整,可生成连续自然的表情动画。     

基于深度卷积网络的3D人脸重构算法

基于单张人脸图片的3D人脸模型重构,无论是在计算机图形领域还是可见光成像领域都是一个极具挑战性的研究方向,对于人脸识别、人脸成像、人脸动画等实际应用更是具有重要意义。针对目前算法复杂度较高、运算量较大且存在局部最优解和初始化不良等问题,本文提出了一种基于深度卷积神经网络的单张图片向3D人脸自动重构算法。该算法首先基于3D转换模型来提取2D人脸图像的密集信息,然后构建深度卷积神经网络架构、设计总体损失函数,直接学习2D人脸图像从像素到3D坐标的映射,从而实现了3D人脸模型的自动构建。算法对比与仿真实验表明,该算法在3D人脸重建上的归一化平均误差更低,且仅需一张2D人脸图像便可自动重构生成3D人脸模型。所生成的3D人脸模型鲁棒性好,重构准确,完整保留表情细节,并且对不同姿态的人脸也具有较好的重建效果,能够在三维空间中无死角自由呈现,将满足更多实际应用需求。     

基于PCA特征提取和距离哈希K近邻分类的人脸表情识别

使用PCA降维,提取人脸表情特征,并结合基于距离的哈希K近邻分类算法进行人脸表情识别。首先使用类Haar特征和AdaBoost算法进行人脸检测,并对人脸图像进行预处理;接着使用PCA提取人脸表情特征,并将特征加入到哈希表;最后使用K近邻分类算法进行人脸表情的识别。将特征库重构为哈希表后,很大地提高了识别效率。     

特定人脸的3D模型生成与应用的研究

计算机3D人脸对象的应用范围十分广泛,包括虚拟现实、辅助教学、远程会议、人机交互、游戏娱乐、电影制作等诸多方面。提出了利用区域差值法的算法实现基于两幅人脸图像生成具有特定人特征的3D人脸模型,并在生成的特定人3D人脸模型的基础上实现了基于MPEG 4的特定人的人脸动画功能,实验取得了良好的效果。     

基于SIFT算法的多表情人脸识别

目前人脸识别系统在识别表情变化的人脸图像时识别准确率会降低,多表情人脸识别在人脸识别领域仍是一个热门的研究方向。本文采用SIFT算法对多表情人脸进行识别,在多表情人脸库上进行了两类仿真实验:实验一中对比了同一个人的不同表情的识别效果,实验二中对比了两个不同的人的相同表情的识别效果,实验结果表明SIFT算法能够克服不同人脸间的整体相似性并能有效提取出人脸的局部细节特征。对Jaffe表情库进行仿真实验,取得了当阈值T=0.35时对多表情人脸图像的正确识别率95.69%,实验结果表明,将SIFT算法应用于多表情人脸识别有巨大的潜在科研价值。     

一种具有噪声鲁棒性的人脸表情识别算法研究

为降低噪声对人脸表情识别的影响,首先提出具有人眼视觉特性的各向异性扩散滤波方法,对图像进行滤波预处理;同时采用改进HOG算子提取人脸表情特征。实验结果表明,改进的各向异性扩散滤波算法在滤除噪声的同时能更好地保留表情图像的弱小细节信息,改进HOG算子相比传统特征提取算子可以更准确地描述人脸表情特征。因此,该算法是一种有效的、具有一定噪声鲁棒性的人脸表情识别算法。     

Facial animation by reverse morphing on a sequence of real images: application to film and video production

Research on facial animation is as vast as the many interests and needs that can be found in the general public, television or film production. For Mac Guff Ligne, a company specialized in the fabrication of special effects and computer generated images, the needs and the constraints on such a topic are very big. Morphing is often used in facial animation, and consists in mixing several expression models. As we will discover, the advantages in using morphing are numerous, but the animation workload remains long and time-consuming. Our goal is to propose a fast and reliable animation tool that is based on the same morphing technique with which the graphic artists are familiar. Our method is to inverse the classical process of morphing, and to match a real facial animation to a 3D facial animation by automatic calculation of the weights of expression models. Firstly, we discretize the real facial animation using a number of characteristic points. Then we follow the path of each point by optic or magnetic motion capture, or through the filmed images. This tracked down animation is then decomposed, for each frame, according to a basis of characteristic expressions (joy, anger, etc.) that can be automatically taken out from the real animation during the calibration stage. It means that we express a simplified shape of the face by linear composition of a series of basic faces. Finally, we can reintroduce the results of this decomposition into a more complex facial morph which has a totally different topology and geometry. The user can thus complete and modify the resulting animation using a tool he knows well. This method, used in production at Mac Guff Ligne, proves to be a solid, effective and easy-to-use work base for facial animation.     

Expression transfer for facial sketch animation

This paper presents a hierarchical animation method for transferring facial expressions extracted from a performance video to different facial sketches. Without any expression example obtained from target faces, our approach can transfer expressions by motion retargetting to facial sketches. However, in practical applications, the image noise in each frame will reduce the feature extraction accuracy from source faces. And the shape difference between source and target faces will influence the animation quality for representing expressions. To solve these difficulties, we propose a robust neighbor-expression transfer (NET) model, which aims at modeling the spatial relations among sparse facial features. By learning expression behaviors from neighbor face examples, the NET model can reconstruct facial expressions from noisy signals. Based on the NET model, we present a hierarchical method to animate facial sketches. The motion vectors on the source face are adjusted from coarse to fine on the target face. Accordingly, the animation results are generated to replicate source expressions. Experimental results demonstrate that the proposed method can effectively and robustly transfer expressions by noisy animation signals.     

人脸动画中基于样条插值的器官拼接算法实现

人脸动画广泛地应用于游戏行业、远程会议、代理和化身等许多其它领域,近年吸引了很多学者的研究,其中口腔／眼睛等器官的动画一直是一个较大的难点。本文提出了一种将口腔／眼睛的器官样本图片融合到人脸图像中并根据单张中性人脸图片生成人脸动画的方法。该方法根据特征点生成样条,在极坐标上对样条插值来实现空间映射,然后采用后向映射和插值进行图像重采样得到融合图像。实验结果表明,该方法产生的融合图片较为自然,能实现口腔／眼球等器官的运动,能满足人脸动画生成的实时性要求。     

Modeling of deformation using NURBS curves as controller

This paper presents a new method in computer facial animation that models facial deformation by modifying the NURBS curve. In this work, displacement vectors of curve points are decomposed into physically meaningful components. Three independent vectors are determined for each curve sample point and the directions of the vectors possess anatomic meaning. The movement of the curve point is then resolved into components along the three vectors. These components can be processed individually to simulate a real face, and then summed again into a vector. The resultant vector can thus affect the polygonal vertices of a face model that are associated with the curve point. This method represents an extension of our previous work in computer facial animation. Experiments suggest this technique can be used to facilitate subtle modeling and animation of facial deformation.     

A new efficient expression generation and automatic cloning method for multimedia actors

This paper describes a new and efficient method for facial expression generation on cloned synthetic head models. The system uses abstract facial muscles called action units (AUs) based on both anatomical muscles and the facial action coding system. The facial expression generation method has real-time performance, is less computationally expensive than physically based models, and has greater anatomical correspondence than rational free-form deformation or spline-based, techniques. Automatic cloning of a real human head is done by adapting a generic facial and head mesh to Cyberware laser scanned data. The conformation of the generic head to the individual data and the fitting of texture onto it are based on a fully automatic feature extraction procedure. Individual facial animation parameters are also automatically estimated during the conformation process. The entire animation system is hierarchical; emotions and visemes (the visual mouth shapes that occur during speech) are defined in terms of the AUs, and higher-level gestures are defined in terms of AUs, emotions, and visemes as well as the temporal relationships between them. The main emphasis of the paper is on the abstract muscle model, along with limited discussion on the automatic cloning process and higher-level animation control aspects.     

Elastic body spline technique for feature point generation and face modeling.

Due to the advent of MPEG-4 standard, facial animation has been receiving significant attention lately. A common approach for facial animation is to use the mesh model. The physics-based transformation, elastic body spline (EBS), has been proposed to deform the facial mesh model and generate realistic expression by assuming the whole facial image has the same elastic property. In this paper, we partition facial images into different regions and propose an iterative algorithm to find the elastic property of each facial region. By doing so, we can obtain the EBS for mesh vertices in the facial mesh model such that facial animation can be more realistically achieved.     

基于LED与肌肉模型的特定人脸建模与动画

特定三维人脸的建模与动画是计算机图形学中一个非常令人感兴趣的领域.本文提出了一种新的从两幅正交照片建立特定人脸的模型以及动画方法,首先以主动轮廓跟踪技术snake自动获取人脸特征点的准确位置,然后以文中的局部弹性变形(local elastic deformation)方法进行通用人脸模型到特定人脸的定制,并辅以采用图像镶嵌技术生成的大分辨率纹理图像施行纹理绘制,该方法以特征点的位移和非特征点与特征点的相对位置为基础计算局部人脸面部的变形,同时还能够实现人脸剧烈的面部变化和动作,与肌肉模型相结合,可很好地实时完成人脸的动画,具有快速高效的特点.最后,给出了所得到的实验结果.     

一种基于共振峰分析的语音驱动人脸动画方法

快速、高效地实现语音驱动下的唇形自动合成,以及优化语音与唇动的同步是语音驱动人脸动画的重点。提出了一种基于共振峰分析的语音驱动人脸动画的方法。对语音信号进行加窗分帧,DFT变换,再对短时音频信号的频谱进行第一、第二共振峰分析,将分析结果映射为一组控制序列,并对控制序列进行去奇异点等后处理。设定三维人脸模型的动态基本口形,以定时方式将控制序列导入模型,完成人脸动画驱动。实验结果表明,该方法简单快速,有效实现了语音和唇形的同步,动画效果连贯自然,可广泛用于各类虚拟角色的配音,缩短虚拟人物的制作周期。