基于单张二维图片的三维人脸建模
|
摘要
人脸是人类日常情感表达和交流最重要、最直接的载体。通过计算机生成具有真实感的三维人脸拥有广阔的应用前景,是近年来计算机图形学、计算机视觉、人工智能等领域中最具挑战性的问题之一。人类视觉系统在识别二维图像的过程中,往往先根据平面图像还原出图像的三维立体信息,人类天生具备从单张平面照片进行三维信息恢复的能力。模拟人类的这一图像认知过程,研究基于单张平面图像的人脸三维建模技术,是当前认知计算中的一个重要问题。
利用三维扫描仪获取三维形状数据和纹理信息是一种直接的人脸建模方法,通常具有较高的精度,但是存在硬件设备造价高、不灵活等不足,一般只适用于某些特殊场合;当前的研究热点主要集中在根据图像和视频序列进行人脸重建,现有基于多张图像的方法普遍存在特征点匹配复杂、效率低等不足。根据单张人脸照片上的少量特征点能够快速、自动地实现特定人脸的建模,是目前三维人脸建模研究中一个极具潜力的研究方向。然而,如何充分地利用少量的信息重建出真实感好的人脸模型是其面临的主要挑战。
本论文以统计学为工具,通过建立人脸统计模型,利用人脸结构先验知识对三维人脸形状的建模进行约束,从而实现了以单张照片上少量特征点为基础的三维人脸建模。针对基于单张照片的三维人脸重建问题,本文的主要研究内容包括:创建标准化的三维人脸库,并以此建立人脸类的统计模型;研究高效的基于特征点的变形算法和人脸建模方案;探索基于三维人脸的应用研究。取得如下研究成果:
1)提出一个基于平面模板的重采样算法,解决了三维人脸稠密点的自动对应问题,实现了人脸库的标准化。
建立标准化的三维人脸数据库是建立人脸统计模型、人脸建模和人脸动画等方面研究的基础性工作。本文在网格重采样方法的启发下,提出一种基于平面模板的方法,可以自动地实现三维人脸间的对应,克服了传统方法对应效果差、手工操作复杂等不足。实验结果表明,经本文算法标准化处理后的人脸库具有较好的对应效果,为建立人脸形状统计模型进行三维人脸建模奠定了基础。(第2章)
2)针对单张平面图片,提出基于人脸二维特征点的三维形变算法。
(?)提出一个全局形变算法——基于动态成分的形变模型(DynamicComponent based Deformation Model,DCDM),通过筛选对建模最有效的主成分,提高了形变算法的精度和稳定性。传统基于主成分分析(Principal Component Analysis,PCA)的形变算法通常选择具有较大特征值的部分主成分构成特征矩阵,这种选择方式会引入不相关信息或者丢失有用信息,为后续建模带来误差。本文提出一个筛选策略,采用t检验对每个主成分进行是否线性相关的显著性检验,选择与当前特定人脸最相关的成分来构成特征矩阵,实验表明DCDM提高了建模的稳定性并降低了建模误差;(第3.3节)
(?)提出一个基于先验知识的局部形变算法——基于Sibson坐标的加权LFA形变(Sibson Weighted Local Feature Analysis,SWLFA)算法,通过计算权值增强了LFA算法的局部性,使之能够根据少量控制点生成真实感较好的人脸形状曲面。针对全局形变算法重建出的人脸形状个性特征不突出的问题,将Sibson坐标用于局部特征分析,实现了基于人脸形状结构知识的局部形变,SWLFA算法以Sibson坐标为权值,既能够避免控制点之间的干扰,具备较强的局部性,又能充分地利用人脸形状的先验信息,保证较为真实的建模效果。(第3.4节)
3)提出两步人脸建模(Two-Step Face Modeling,TSFM)方案,通过对三维人脸库知识的学习,实现了对单张图片上人脸特征点的深度估计,提高了形变算法在三维人脸深度方向(Z轴)上的重建精度。由于单张照片上的人脸特征点的深度信息未知,仅通过形变算法的改进对建模精度的提高有限。本文探讨了特征点深度估计的三种方法,指出本文提出的基于稀疏线性模型的优化算法能够相对准确、稳定地估计出二维特征点的深度信息。实验结果表明,将深度估计值应用于形变算法,可以提高人脸的重建精度。另外,TSFM不仅适用于基于统计模型的形变算法,还能改善其它插值算法在深度方向上的建模性能。(第4.2节)
4)以重建的三维人脸模型为基础,解决了光照估计和姿态估计问题,并进行了三维人脸动画的研究。
(?)通过建立三维中性人脸与输入人脸图像顶点的对应关系,估计人脸图像上每个像素的法向量,并采用球面谐波模型实现任意光照条件下单张照片人脸的光照估计和补偿。实验结果表明,人脸图像经光照补偿后能够明显提高人脸识别率;(第5.2节)
(?)根据三维人脸模型与输入照片上人脸特征点之间的对应关系,采用线性回归实现了输入照片的人脸姿态角估计。实验结果表明,相对已有算法,该算法能够提高单轴、多轴偏转角度的估计精度;(第5.3节)
(?)采用一个三层运动控制方案,实现在特征点、器官和表情合成三个层次上的控制,并开发了一套人脸表情动画系统。运动控制采用了MPEG4标准,具有自动化程度高、通用性强的特点。实验结果表明,本系统能够生成逼真的三维人脸表情动画。(第6章)
Human face is the most significant and essential carrier of emotional expression and people's daily communication. There are broad potential applications to model realistic 3D human face automatically using computer techniques, which is a challenging topic in the fields of computer graphics (CG), computer vision (CV) and artificial intelligence (AI). Human beings are born with a capacity of recovering 3D information from single image by human visual system (HVS). It is an essential problem in cognitive computing to develop new technologies for modeling 3D human face from a 2D image through simulating the cognitive procedure of HVS.
Capturing shape and texture information using 3D laser-scanner is a straightforward method which is more accurate than others. Unfortunately, it can only be installed in a certain special situations due to the high cost of the equipments and its inflexibility. Therefore, current hotspots of face modeling focus on image based methods. However, high complexities of feature matching process and inefficiency are the main limitations of these methods. Modeling a 3D face from a few feature points on one image is a promising direction that could run quickly and automatically. Nevertheless, the primary challenge of this method is how to make full use of the small quantity of facial information to improve quality of the reconstructed 3D face.
In this thesis, a human facial shape statistic model——extracted from a 3Dface database——is built as a prior knowledge to constrain the procedure of facemodeling. The main content of this thesis includes: establish a statistic model of human face shape by creating a standardized 3D face database; develop effective modeling algorithms and schemes for 3D face modeling; explore 3D face applications. And, the main contributions are listed as follows:
1) By solving the correspondence between faces automatically, a 2D templatebased alignment algorithm is developed to create a standardized 3D facedatabase.
It's a fundamental job to create a standardized 3D face database for building a face statistic model and for face modeling and animation. Inspired by the idea of mesh re-sampling, we propose a novel 2D template based alignment algorithm which could be implemented automatically and overcomes the main shortcomings of traditional methods, i.e., imprecise and operational complexity. Experiment results show that the standardized database created by our method has considerable good correspondence effects. It is easy to create a statistic model of facial shape, which lays a good foundation for 3D face modeling. (Chapter 2)
2) Develop 3D face deformation algorithms based on features of a 2D image.
A global deformation algorithm—Dynamic Component based Deformation Model (DCDM) is proposed, which could improve the precise and stability of deformation algorithm by selecting the most effective components in face modeling. Principal Component Analysis (PCA) based methods always use the prior components (eigenvectors) with the maximum eigenvalues to construct an eigenmatrix. This conventional strategy may import some irrelevant factors, or lose some useful ones, resulting in errors for the modeling process. We propose a dynamic component based deformation model that uses t-test to determine the correlativity for each component to the novel face at first, and then concatenate the most correlative ones to form an eigenmatrix. Experiment results show that the faces modeled by DCDM are more stable and more accurate. (Section 3.3)
A local deformation algorithm based on prior knowledge—Sibson Weighted Local Feature Analysis (SWLFA)—is proposed, which could create smooth 3D face shape by allocating weights for each control point used by LFA. Since 3D faces created by global deformation method lack some personalities, we apply Sibson coordinate to local features analysis, a local deformation algorithm (SWLFA) is hence proposed based on prior knowledge of facial shape. SWLFA has strong local properties by eliminating the interactional impacts between control points. It could elaborately depict personality traits on human faces benefiting from making full use of the prior assumptions regarding facial characteristics. (Section 3.4)
3) A Two-Step Face Modeling (TSFM) scheme is proposed to improve the fitting result in the direction of Z-axis. This is achieved by estimating features' depth from prior knowledge of human shape. We find that improvements are limited by just tuning the performance of deformation methods due to the lack of depth information of the facial features from only one image. By investigating three methods for feature's depth estimation, we indicate that the proposed Sparse Linear Model based Optimization in this thesis is more accurate and stable than the other two. Comparison tests show that, the estimated depth information can be used to improve the accuracy of human face reconstruction. Moreover, TSFM could improve the precision of facial shape reconstruction of both interpolation methods and statistical deformation methods. (Section 4.2)
4) Based on a reconstructed 3D face, the problems of illumination, pose estimation and 3D face animation are further studied.
The normal of each pixel on a 2D image face is estimated by establishing the correspondence between a 3D average face and the input facial image. Then, the spherical harmonic model is used for calculating and compensating illumination condition of the given image. Experiment results show that after illumination compensation, the recognition rate is significantly improved. (Section 5.2)
Based on the point-to-point relationship between features on 3D face model and 2D image, we adopt a linear regression model to estimate the pose of the head on the input image. The comparison results show that the revolving angles estimated by our algorithm are more accurate than existing methods on both multi-axis and single axis. (Section 5.3)
A three-layer control model is adopted to generate new expressions based on 3 levels—features, organs and expression. Base upon this, a 3D face animation system is developed. By using the MPGE4 standard, our system is highly automatic and general-purpose. Experiment results show that realistic 3D expressions animation could be generated by this system. (Chapter 6)
利用三维扫描仪获取三维形状数据和纹理信息是一种直接的人脸建模方法,通常具有较高的精度,但是存在硬件设备造价高、不灵活等不足,一般只适用于某些特殊场合;当前的研究热点主要集中在根据图像和视频序列进行人脸重建,现有基于多张图像的方法普遍存在特征点匹配复杂、效率低等不足。根据单张人脸照片上的少量特征点能够快速、自动地实现特定人脸的建模,是目前三维人脸建模研究中一个极具潜力的研究方向。然而,如何充分地利用少量的信息重建出真实感好的人脸模型是其面临的主要挑战。
本论文以统计学为工具,通过建立人脸统计模型,利用人脸结构先验知识对三维人脸形状的建模进行约束,从而实现了以单张照片上少量特征点为基础的三维人脸建模。针对基于单张照片的三维人脸重建问题,本文的主要研究内容包括:创建标准化的三维人脸库,并以此建立人脸类的统计模型;研究高效的基于特征点的变形算法和人脸建模方案;探索基于三维人脸的应用研究。取得如下研究成果:
1)提出一个基于平面模板的重采样算法,解决了三维人脸稠密点的自动对应问题,实现了人脸库的标准化。
建立标准化的三维人脸数据库是建立人脸统计模型、人脸建模和人脸动画等方面研究的基础性工作。本文在网格重采样方法的启发下,提出一种基于平面模板的方法,可以自动地实现三维人脸间的对应,克服了传统方法对应效果差、手工操作复杂等不足。实验结果表明,经本文算法标准化处理后的人脸库具有较好的对应效果,为建立人脸形状统计模型进行三维人脸建模奠定了基础。(第2章)
2)针对单张平面图片,提出基于人脸二维特征点的三维形变算法。
(?)提出一个全局形变算法——基于动态成分的形变模型(DynamicComponent based Deformation Model,DCDM),通过筛选对建模最有效的主成分,提高了形变算法的精度和稳定性。传统基于主成分分析(Principal Component Analysis,PCA)的形变算法通常选择具有较大特征值的部分主成分构成特征矩阵,这种选择方式会引入不相关信息或者丢失有用信息,为后续建模带来误差。本文提出一个筛选策略,采用t检验对每个主成分进行是否线性相关的显著性检验,选择与当前特定人脸最相关的成分来构成特征矩阵,实验表明DCDM提高了建模的稳定性并降低了建模误差;(第3.3节)
(?)提出一个基于先验知识的局部形变算法——基于Sibson坐标的加权LFA形变(Sibson Weighted Local Feature Analysis,SWLFA)算法,通过计算权值增强了LFA算法的局部性,使之能够根据少量控制点生成真实感较好的人脸形状曲面。针对全局形变算法重建出的人脸形状个性特征不突出的问题,将Sibson坐标用于局部特征分析,实现了基于人脸形状结构知识的局部形变,SWLFA算法以Sibson坐标为权值,既能够避免控制点之间的干扰,具备较强的局部性,又能充分地利用人脸形状的先验信息,保证较为真实的建模效果。(第3.4节)
3)提出两步人脸建模(Two-Step Face Modeling,TSFM)方案,通过对三维人脸库知识的学习,实现了对单张图片上人脸特征点的深度估计,提高了形变算法在三维人脸深度方向(Z轴)上的重建精度。由于单张照片上的人脸特征点的深度信息未知,仅通过形变算法的改进对建模精度的提高有限。本文探讨了特征点深度估计的三种方法,指出本文提出的基于稀疏线性模型的优化算法能够相对准确、稳定地估计出二维特征点的深度信息。实验结果表明,将深度估计值应用于形变算法,可以提高人脸的重建精度。另外,TSFM不仅适用于基于统计模型的形变算法,还能改善其它插值算法在深度方向上的建模性能。(第4.2节)
4)以重建的三维人脸模型为基础,解决了光照估计和姿态估计问题,并进行了三维人脸动画的研究。
(?)通过建立三维中性人脸与输入人脸图像顶点的对应关系,估计人脸图像上每个像素的法向量,并采用球面谐波模型实现任意光照条件下单张照片人脸的光照估计和补偿。实验结果表明,人脸图像经光照补偿后能够明显提高人脸识别率;(第5.2节)
(?)根据三维人脸模型与输入照片上人脸特征点之间的对应关系,采用线性回归实现了输入照片的人脸姿态角估计。实验结果表明,相对已有算法,该算法能够提高单轴、多轴偏转角度的估计精度;(第5.3节)
(?)采用一个三层运动控制方案,实现在特征点、器官和表情合成三个层次上的控制,并开发了一套人脸表情动画系统。运动控制采用了MPEG4标准,具有自动化程度高、通用性强的特点。实验结果表明,本系统能够生成逼真的三维人脸表情动画。(第6章)
Human face is the most significant and essential carrier of emotional expression and people's daily communication. There are broad potential applications to model realistic 3D human face automatically using computer techniques, which is a challenging topic in the fields of computer graphics (CG), computer vision (CV) and artificial intelligence (AI). Human beings are born with a capacity of recovering 3D information from single image by human visual system (HVS). It is an essential problem in cognitive computing to develop new technologies for modeling 3D human face from a 2D image through simulating the cognitive procedure of HVS.
Capturing shape and texture information using 3D laser-scanner is a straightforward method which is more accurate than others. Unfortunately, it can only be installed in a certain special situations due to the high cost of the equipments and its inflexibility. Therefore, current hotspots of face modeling focus on image based methods. However, high complexities of feature matching process and inefficiency are the main limitations of these methods. Modeling a 3D face from a few feature points on one image is a promising direction that could run quickly and automatically. Nevertheless, the primary challenge of this method is how to make full use of the small quantity of facial information to improve quality of the reconstructed 3D face.
In this thesis, a human facial shape statistic model——extracted from a 3Dface database——is built as a prior knowledge to constrain the procedure of facemodeling. The main content of this thesis includes: establish a statistic model of human face shape by creating a standardized 3D face database; develop effective modeling algorithms and schemes for 3D face modeling; explore 3D face applications. And, the main contributions are listed as follows:
1) By solving the correspondence between faces automatically, a 2D templatebased alignment algorithm is developed to create a standardized 3D facedatabase.
It's a fundamental job to create a standardized 3D face database for building a face statistic model and for face modeling and animation. Inspired by the idea of mesh re-sampling, we propose a novel 2D template based alignment algorithm which could be implemented automatically and overcomes the main shortcomings of traditional methods, i.e., imprecise and operational complexity. Experiment results show that the standardized database created by our method has considerable good correspondence effects. It is easy to create a statistic model of facial shape, which lays a good foundation for 3D face modeling. (Chapter 2)
2) Develop 3D face deformation algorithms based on features of a 2D image.
A global deformation algorithm—Dynamic Component based Deformation Model (DCDM) is proposed, which could improve the precise and stability of deformation algorithm by selecting the most effective components in face modeling. Principal Component Analysis (PCA) based methods always use the prior components (eigenvectors) with the maximum eigenvalues to construct an eigenmatrix. This conventional strategy may import some irrelevant factors, or lose some useful ones, resulting in errors for the modeling process. We propose a dynamic component based deformation model that uses t-test to determine the correlativity for each component to the novel face at first, and then concatenate the most correlative ones to form an eigenmatrix. Experiment results show that the faces modeled by DCDM are more stable and more accurate. (Section 3.3)
A local deformation algorithm based on prior knowledge—Sibson Weighted Local Feature Analysis (SWLFA)—is proposed, which could create smooth 3D face shape by allocating weights for each control point used by LFA. Since 3D faces created by global deformation method lack some personalities, we apply Sibson coordinate to local features analysis, a local deformation algorithm (SWLFA) is hence proposed based on prior knowledge of facial shape. SWLFA has strong local properties by eliminating the interactional impacts between control points. It could elaborately depict personality traits on human faces benefiting from making full use of the prior assumptions regarding facial characteristics. (Section 3.4)
3) A Two-Step Face Modeling (TSFM) scheme is proposed to improve the fitting result in the direction of Z-axis. This is achieved by estimating features' depth from prior knowledge of human shape. We find that improvements are limited by just tuning the performance of deformation methods due to the lack of depth information of the facial features from only one image. By investigating three methods for feature's depth estimation, we indicate that the proposed Sparse Linear Model based Optimization in this thesis is more accurate and stable than the other two. Comparison tests show that, the estimated depth information can be used to improve the accuracy of human face reconstruction. Moreover, TSFM could improve the precision of facial shape reconstruction of both interpolation methods and statistical deformation methods. (Section 4.2)
4) Based on a reconstructed 3D face, the problems of illumination, pose estimation and 3D face animation are further studied.
The normal of each pixel on a 2D image face is estimated by establishing the correspondence between a 3D average face and the input facial image. Then, the spherical harmonic model is used for calculating and compensating illumination condition of the given image. Experiment results show that after illumination compensation, the recognition rate is significantly improved. (Section 5.2)
Based on the point-to-point relationship between features on 3D face model and 2D image, we adopt a linear regression model to estimate the pose of the head on the input image. The comparison results show that the revolving angles estimated by our algorithm are more accurate than existing methods on both multi-axis and single axis. (Section 5.3)
A three-layer control model is adopted to generate new expressions based on 3 levels—features, organs and expression. Base upon this, a 3D face animation system is developed. By using the MPGE4 standard, our system is highly automatic and general-purpose. Experiment results show that realistic 3D expressions animation could be generated by this system. (Chapter 6)
引文
[1]United Nations DOEASAU.Population Division:World Population Prospects.The 2006 Revision,CD-ROM Edition,Extended Dataset[EB/OL].New York:2007.
[2]山世光.人脸识别中若干关键问题的研究[D].博士.北京:中科院计算所,2004.
[3]柴秀娟,山世光,卿来云.基于3D人脸重建的光照、姿态不变人脸识别[J].软件学报.2006,17(3):525-534.
[4]Parke F I.Computer generated animation of faces[C].Proceedings of the ACM annual conference,Boston,Massachusetts,United States,1972:451-457.
[5]徐琳,袁保宗,高文.真实感人脸建模研究的进展与展望[J].软件学报.2003,14(4):804-810.
[6]徐成华,王蕴红,谭铁牛.三维人脸建模与应用[J].中国图象图形学报.2004,9(8):893-903.
[7]Lee S Y,Chwa K Y,Shin S Y.Image metamorphosis using snakes and free-form deformations[C].Proceedings of the 22nd annual conference on Computer graphics and interactive techniques,1995:439-448.
[8]Xu C,Quan L,Wang Y.Adaptive multi-resolution fitting and its application to realistic head modeling[C].Geometric Modeling and Processing,Beijing,China,2004:345-348.
[9]胡永利,尹宝才,程世铨.创建中国人三维人脸库关键技术研究[J].计算机研究与发展.2005,42(4):622-628.
[10]Zha H,Wang P.Realistic Face Modeling by Registration of 3-D Mesh Models and Multi-View Color Images[C].Proceeding of the 8th Int Conf Computer Aided Design and Computer Graphics,Oct.28-31,2003,Macao,China,2003:217-222.
[11]Lee Y,Terzopoulos D,Walters K.Realistic modeling for facial animation[C].In SIGGRAPH'95 Conference Proceedings:ACM press,Los Angels,1995:55-62.
[12]刘晓宁.基于三维模型的人脸识别技术研究[D].博士学位论文.西北工业大学,2006.
[13]Waters K,Terzopoulos D.Modeling and animating faces using scanned data[J].Visualization and Computer Animation.1991,2(4):123-128.
[14]Posdamer J L,Altschuler M D.Surface measurement by space-encoded projected beam systems[J].Computer Graphics and Image Processing.1982,18(1):1-17.
[15]Beumier C,Acheroy M.3D facial surface acquisition by structured light[C].International Workshop on Synthetic-Natural Hybrid Coding and Three Dimensional Imaging,Santorini,Greece,1999:103-106.
[16]Debevec P,Hawkins T,Tchou C.Acquiring the Reflectance Field of a Human Face[C].SIGGRAPH 2000 Conference,New Orleans,2000:145-156.
[17]Tarini M,Yamauchi H,Haber J.Texturing Faces[C].Graphics Interface 2002 Conference,Calgary,Canada,2002:89-98.
[18]Ikeuchi K,Horn B K P.Numerical shape from shading and occluding boundaries[M].Shape from shading,MIT Press,1989,245-299.
[19]Blake A,Zimmerman A,Knowles G.Surface descriptions from stereo and shading[J].Image and Vision Computing.1986,3(4):183-191.
[20]Pentland A P.Local shading analysis[M].Shape from shading,MIT Press,1989,443-487.
[21]Pentland A.Shape Information From Shading:A Theory About Human Perception[C].Second International Conference on Computer Vision,Florida,USA,1988:404-413.
[22]Samaras D,Metaxas D.Incorporating Illumination Constraints in Deformable Models for Shape from Shading and Light Direction Estimation[J].IEEE Trans.PAMI.2003,25(2):247-264.
[23]Zhao W Y,Chellappa R.Symmetric Shape-from-Shading Using Self-ratio Image[J].Int.J.Comput.Vision.2001,45(1):55-75.
[24]Smith W A P,Hancock E R.Recovering Facial Shape Using a Statistical Model of Surface Normal Direction[J].IEEE Trans.PAMI.2006,28(12):1914-1930.
[25]王琨,郑南宁.基于SFM算法的三维人脸模型重建[J].计算机学报.2005,28(6):1048-1053.
[26]Sengupta K,Ko C C.Scanning face models with desktop cameras[J].IEEE Transactions on Industrial Electronics.2001,48(5):904-912.
[27]沈晔湖,刘济林.利用立体图对的三维人脸模型重建算法[J].计算机辅助设计与图形学学报.2006,18(12):1904-1910.
[28]Pighin F,Hecker J,Lischinski D.Synthesizing realistic facial expressions from photographs[C].Proceedings of the 25th annual conference on Computer graphics and interactive techniques,1998:75-84.
[29]Dimitrijevic M,Ilic S F P.Accurate face models from uncalibrated and ill-lit video sequence[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Jun 27-Jul 2,2004,Washington,DC,USA,2004:188-202.
[30]Liu Z,Zhang Z,Chuck J.Rapid modeling of animated faces from video[J]. The Journal of Visualization and Computer Animation.2001,12(4):227-240.
[31]Shan Y,Liu Z,Zhang Z.Model-based Bundle Adjustment with Application to Face Modeling[C].Eighth IEEE International Conference on Computer Vision,Vancouver,BC,Canada,2001:644-651.
[32]梁荻,苏志勋.基于正交照片的人脸重建技术[J].系统仿真学报.2003,15(11):1646-1650.
[33]晏洁,高文,尹宝才.具有真实感的三维虚拟特定人脸生成方法[J].计算机学报.1999,22(2):147-153.
[34]梅丽,鲍虎军,彭群生.特定人脸的快速定制和肌肉驱动的表情动画[J].计算机辅助设计与图形学学报.2001,13(12):1077-1082.
[35]王鑫,孙守迁,陈廓.基于区域控制模型的三维人脸重建技术[J].计算机辅助设计与图形学学报.2007,119(18):1046-1050.
[36]高鹏,东彭翔,田劲东.三维人脸建模中面部特征轮廓线的提取[J].系统仿真学报.2006,18(8):2105-2113.
[37]彭翔,高鹏东,刘晓利.真实感人脸模型的细分曲面重建[J].计算机辅助设计与图形学学报.2006,18(5):744-747.
[38]魏诗国.素描[M].北京:高等教育出版社,1999.
[39]Rudomin I,Bojorquez A,Cuevas H.Statistical Generation of 3D Facial Animable Models[C].Proceedings of the Shape Modeling International 2002,2002:219.
[40]Iwasa T,Shima T,Sai M.3D Eigenfaces for face modeling[C].Proceedings 5th Asian Conference on Computer Vision,2002:1-6.
[41]Blanz V,Vetter T.A morphable model for the synthesis of 3D faces[C].Proceedings of the 26th annual conference on Computer graphics and interactive techniques,1999:187-194.
[42]Ullman S,Basri R.Recognition by Linear Combination of Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1991,13(10):992-1006.
[43]Shashua A.Projective Structure from two Uncalibrated Images:Structure from Motion and Recognition[R].Massachusetts Institute of Technology,1992.
[44]Poggio T,Vetter T.Recognition and Structure from one 2D Model View:Observations on Prototypes,Object Classes and Symmetries[R].Massachusetts Institute of Technology,1992.
[45]Vetter T,Poggio T.Linear object classes and image synthesis from a single example image[J].IEEE Trans.PAMI.1997,19(7):733-742.
[46]Blanz V,Basso C,Poggio T.Reanimating Faces in Images and Video[C].EUROGRAPHICS,Granada,Spain,2003:641-650.
[47]Blanz V,Vetter T.Face recognition based on fitting a 3D morphable model[J].IEEE Trans.PAMI.2003,25(9):1063-1074.
[48]Blanz V,Grother P,Phillips P J.Face recognition based on frontal views generated from non-frontal images[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:454-461.
[49]Romdhani S.Face image analysis using a multiple feature fitting strategy[D].Ph.D.thesis.Basel,Switzerland:University of Basel,,2005.
[50]胡永利,尹宝才,谷春亮.基于形变模型的三维人脸重建方法及其改进[J].计算机学报.2005,28(10):1671-1679.
[51]胡永利.真实感三维人脸建模及应用研究[D].博士学位论文.北京工业大学,2004.
[52]王成章,尹宝才,孙艳丰.改进的基于形变模型的三维人脸建模方法[J].自动化学报.2007,33(3):232-239.
[53]谷春亮,尹宝才,孔德慧.基于三维多分辨率模型与Fisher线性判别的人脸识别方法[J].计算机学报.2005,25(1):97-104.
[54]Basri R,Jacobs D W.Lambertian Reflectance and Linear Sub-spaces[J].IEEE Trans.PAMI.2003,25(2):218-233.
[55]郑南宁,付昀,张婷.人脸的表情与年龄变换和非完整信息的重构技术(上)[J].电子学报.2003,31(12A):1955-1962.
[56]付昀,郑南宁,张婷.人脸的表情与年龄变换和非完整信息的重构技术(下)[J].电子学报.2003,31(12A):1963-1970.
[57]Fu Y,Zheng N.M-Face:An Appearance-Based Photorealistic Model for Multiple Facial Attributes[J].IEEE Trans.CSVT.2006,16(7):830-842.
[58]裴玉茹,查红彬.真实感人脸的形状与表情空间[J].计算机辅助设计与图形学学报.2006,18(5):613-619.
[59]Amberg B,Blake A,Fitzgibbon A.Reconstructing High Quality Face-Surfaces using Model Based Stereo[C].IEEE 11th International Conference on Computer Vision,2007,Rio de Janeiro,Brazil,2007:1-8.
[60]Blanz V,Mehl A,Vetter T.A statistical method for robust 3D surface reconstruction from sparse data[C].2nd International Symposium on 3D Data Processing,Visualization,Thessaloniki,Greece,2004:293-300.
[61]Jiang D,Hu Y,Yan S.Efficient 3D reconstruction for face recognition[J].Pattern Recognition.2005,38(6):787-798.
[62]Knothe R,Romdhani S,Vetter T.Combining PCA and LFA for Surface Reconstruction from a Sparse Set of Control Points[C].7th International Conference on Automatic Face and Gesture Recognition,2006:637-644.
[63]Parke F I.A model for human faces that allows speech synchronized animation[C].The 1st annual conference on Computer graphics and interactive techniques,Boulder,Colorado,1974:2.
[64] Parke F I. Parameterized Models for Facial Animation[J]. IEEE Comput.Graph.Appl. 1982, 2(9): 61-68.
[65] Parke F, Waters K. Computer Facial Animation[M]. Wellesley, MA: A. K.Peters, 1996.
[66] Ekman P, Friesen W V. Manual for the facial action coding system[M].Palo Alto: Consulting Psychologists Press, 1977.
[67] Platt S M, Badler N I. Animating facial expressions[J]. SIGGRAPH Comput. Graph. 1981, 15(3): 245-252.
[68] Waters K. A muscle model for animation three-dimensional facial expression[C]. International Conference on Computer Graphics and Interactive Techniques, 1987: 17-24.
[69] Thalmann N, Primeau N, Thalmann D. Abstract muscle action procedures for human face animation[J]. Visual Computer. 1988, 3(5): 290-297.
[70] Thalmann N M, Cazedevals A, Thalmann D. Modelling Facial Communication between an Animator and a Synthetic Actor in Real Time[C].Modeling in Computer Graphics, Genova, Italy, 1993: 387-396.
[71] Sederberg T W, Parry S R. Free-form deformation of solid geometric models[J]. SIGGRAPH Comput. Graph. 1986, 20(4): 151-160.
[72] Coquillart S. Extended free-form deformation: a sculpturing tool for 3D geometric modeling[C]. 17th annual conference on Computer graphics and interactive techniques, Dallas, TX, USA, 1990: 187-196.
[73] Wang C L Y, Forsey D R. Langwidere: a new facial animation system[C].Proceedings of Computer Animation apos, Geneva,Switzerland, 1994: 59-68.
[74] Tony D, Michael K, Truong T. Subdivision surfaces in character animation[C]. International Conference on Computer Graphics and Interactive Techniques, 1998: 85-94.
[75] Reeves W. Simple and complex facial animation: Case studies[C].SIGGRAPH'90, 1990:88-106.
[76] Eisert P, Girod B. Analyzing Facial Expressions for Virtual Conferencing[J]. IEEE Comput. Graph. Appl. 1998, 18(5): 70-78.
[77] Cootes T F, Edwards G J, Taylor C J. Active appearance models[J]. IEEE Trans. PAMI. 2001, 23(6): 681-685.
[78] Vetter T, Romdhani S. Face Modelling and Recognition Tutorial (2)[C].The 8th European Conference on Computer Vision, Prague , Czech, 2004.
[79] The BJUT-3D Large-Scale Chinese Face Database, Technical Report No ISKL-TR-05-FMFR-001, Multimedia Tech & Graphic Lab, Beijing University of Technology[R]. http://www.bjut.edu.cn/sci/multimedia/mul-1ab/3dface/,2005.
[80] Vetter T, Blanz V. Estimating coloured 3d face models from single images:An example based approach[C]. European Conference on Computer Vision'98,Freiburg, Germany, 1998: 499-513.
[81] Vetter T, Jones M J, Poggio T. A bootstrapping algorithm for learning linear models of object classes[C]. IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico,USA, 1997: 40-47.
[82] Gu C, Yin B, Hu Y. Resampling Based Method for Pixel-wise Correspondence between 3D Faces[C]. International Conference on Information Technology: Coding and Computing, 2004: 614-619.
[83] 尹宝才,何晏晏,孙艳丰.三维人脸的非均匀重采样对齐算法[J].北京工业大学学报. 2007, 33(2): 213-218.
[84] Farkas L G. Anthropometry of the Head and Face, 2nd edition[M]. New York: Raven Press, 1994.
[85] Sobottka K, Pitas I. A Fully Automatic Approach to Facial Feature Detection and Tracking[C]. The First International Conference on Audio- and Video-Based Biometric Person Authentication, 1997: 77-84.
[86] Garland M, Heckbert P S. Surface simplification using quadric error metrics[C]. Computer Graphics Proceedings (SIGGRAPH 97), 1997: 209-216.
[87] Romdhani S, Vetter T. Efficient, Robust and Accurate Fitting of a 3D Morphable Model[C]. Ninth IEEE International Conference on Computer Vision - Volume 2, 2003: 59-66.
[88] Blanz V, Vetter T. Reconstructing the complete 3D shape of faces from partial information[J]. Informationsetechnik und Technische Informatik. 2002,44(6): 295-302.
[89] Moccozet L, Thalmann N M. Dirichlet Free-Form Deformations and their Application to Hand Simulation[C]. Proceedings of the Computer Animation,1997: 93-102.
[90] Penev P S, Atick J J. Local Feature Analysis: A general statistical theory for object representation[J]. Network: Computation in Neural Systems. 1996,7(3): 477-500.
[91] Cootes T F, Taylor C J, Cooper D H. Active shape models\—their training and application[J]. Comput. Vis. Image Underst. 1995, 61(1): 38-59.
[92] Turk M, Pentland A. Eigenfaces for recognition[J]. J. Cognitive Neuroscience. 1991, 3(1): 71-86.
[93] Duda R O, Hart P E, Stork D G. Pattern Classification(2nd Edition)[M].Wiley-Interscience, 2000: 680.
[94] Gong X, Wang G. Realistic face modeling based on multiple deformations[J]. The Journal of China Universities of Posts and Telecommunications. 2007, 14(4): 110-117.
[95] Gong X, Wang G. A Dynamic Component Deforming Model for Face Shape Reconstruction[C]. International Symposium on Visual Computing 2007,Lake Tahoe, NV, United States, 2007: 488-497.
[96] Lee W, Magnenat-thalmann N. Fast head modeling for animation[J]. Image and Vision Computing. 2000, 18(4): 355-364.
[97] 王鹏.三维人脸建模中的纹理映射研究[D].硕士.北京:北京大学,2004.
[98] Gong X, Wang G. An automatic approach for pixel-wise correspondence between 3D faces[C]. International Conference on Hybrid Information Technology, Cheju Island, Korea, 2006: 198-205.
[99] Criminisi A, Perez P, Toyama K. Object removal by exemplar-based inpainting[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C], Wisconsin, USA, 2003: 18-20.
[100] Gao W, Cao B, Shan S. The CAS-PEAL Large-Scale Chinese Face Database and Evaluation Protocols[R]. Technical Report No.JDL_TR_04_FR_001, Joint Research & Development Laboratory, CAS, 2004.
[101] Chan H, Bledsoe W W. A man-machine facial recognition system: some preliminary results[R]. Panoramic Research, 1965.
[102] Philips P J, Grother P J, Micheals R J. Face Recognition Vendor Test 2002:Evaluation report[R]. National Institute of Standards and Technology, 2003.
[103] Eriksson, Weber D. Towards 3-dimensional face recognition[C]. In 5th IEEE AFRICON, 1999: 401-406.
[104] Verier T, Poggio T. Linear object classes and image synthesis from a single example image[J]. IEEE Trans. PAMI. 1997, 19(7): 733-741.
[105] Adinl Y, Mcees Y, Ullman S. Face recognition: the problem of compensating for changes in illumination direction[J]. IEEE Trans. PAMI.1997, 19(7): 721-732.
[106] Moghaddara B. Principal manifolds and probabilistic subspaces for visual recognition[J]. IEEE Trans. PAMI. 2002, 24(6): 708-788.
[107] Basria R, Jacobs D. Lambertian reflectance and linear subspaees[J]. IEEE Trans. PAMI. 2003, 25(2): 218-233.
[108] Hallinan P. A low-dimensional representation of human faces for arbitrary lighting conditions[C]. CVPR'94, Seattle Washington, 1994: 995-999.
[109] Basria R, Jacobs D. Lambertian reflectance and linear subspaces[C].ICCV'01, Vancouver,Canada, 2001: 383-390.
[110] Ramamoorthi R. Analytic PCA construction for theoretical analysis of lighting variability in Images of a lambertian object[J]. IEEE Trans. on PAMI. 2002,24(10):1-12.
[111]Georghiades A S,Belhumeur P N,Kriegrnan D J.From few to many illumination cone models for face recognition under differing pose and lighting[J].IEEE Trans.PAMI.2001,23(6):643-660.
[112]Sim T,Kanade T.Combining models and exemplars for face recognition:an illuminating example[C].Workshop on Models versus Exemplars in Computer Vision with CVPR01,2001:47-56.
[113]Lee K C,Ho J,Kreigman D.Nine points of light:acquiring subspaces for face recognition under variable lighting[C].CVPR'01,Kauai,Hawaii,2001:519-526.
[114]Zhang L,Samaras D.Face recognition under variable lighting using harmonic image exemplars[C].CVPR'03,Madison,Wisconsin,2003:19-25.
[115]卿来云,山世光,高文.基于球面谐波基图像的任意光照下的人脸识别[J].计算机学报.2006,29(5):760-768.
[116]Chen Q,Wu H,Fukumoto T.3D head pose estimation without feature tracking[C].The Third IEEE International Conference on Automatic Face and Gesture Recognition,Nara,1998:88-93.
[117]叶航军,白雪生,徐光.基于支持向量机的人脸姿态判定[J].清华大学学报.2003,43(1):67-70.
[118]Nikolaidis A,Pitas I.Facial feature extraction and determination of pose[J].Pattern Recognition.2000,33(11):1783-1791.
[119]梁国远,查红彬,刘宏.基于三维模型和仿射对应原理的人脸姿态估计方法[J].计算机学报.2005,28(5):792-799.
[120]Lopez R,Huang T S.3D Head pose computation from 2D images:template versus features[C].IEEE International Conference on Image Processing,Singapore,1995:599-602.
[121]Shimizu I,Zhang Z,Akamatsu S.Head pose determination from one image using a genetic model[C].IEEE International Conference on Automatic Face and Gesture Recognition,Nara,1998:100-105.
[122]Yang R,Zhang Z.Model-based head pose tracking with stereo vision[C].IEEE International Conference on Automatic Face and Gesture Recognition,2002:255-260.
[123]Georghiades A S,Belhumeur P N,Kriegman D J.From Few to Many:Illumination Cone Models for Face Recognition under Variable Lighting and Pose[J].IEEE Trans.PAMI.2001,23(6):643-660.
[124]Yao P,Evans G,Calway A.Using affine correspondence to estimate 3-D facial pose[C].IEEE International Conference on Image Processing,2001:919-922.
[125]Arai K,Kurihara T,Anjyo K.Bilinear interpolation for facial expression and metamorhposis in real-time animation[J].The Visual Computer.1996,12(3):105-116.
[126]Cohen M,Massara D.Modeling co-articulation in synthetic visual speech[C].Model and Technique in Computer Animation,Tokyo,1993:139-156.
[127]姜大龙,王兆其,高文.基于MPEG-4的三维人脸动画实现方法[J].系统仿真学报.2001(s2):493-496.
[128]姜大龙,高文,王兆其.面向纹理特征的真实感三维人脸动画方法[J].计算机学报.2004,27(6):750-757.
[129]王奎武,王洵,董兰芳.一个MPEG4兼容的人脸动画系统[J].计算机研究与发展.2001,38(5):529-535.
[130]Hu Y,Yin B,Sun Y.3D Face Animation Based on Morphable Model[J].Journal of Information & Computational Science.2005,2(1):35-39.
[131]王成章,尹宝才,白晓明.一种兼容于MPEG-4的三维人脸动画[J].北京工业大学学报.2007,33(10):1102-1106.
[132]Lang C.Kriging Interpolation[R].http://www.nbb.cornell.edu/neurobio/land/OldStudentProjects/cs490-94to95/clang/kriging.html,1998.
[2]山世光.人脸识别中若干关键问题的研究[D].博士.北京:中科院计算所,2004.
[3]柴秀娟,山世光,卿来云.基于3D人脸重建的光照、姿态不变人脸识别[J].软件学报.2006,17(3):525-534.
[4]Parke F I.Computer generated animation of faces[C].Proceedings of the ACM annual conference,Boston,Massachusetts,United States,1972:451-457.
[5]徐琳,袁保宗,高文.真实感人脸建模研究的进展与展望[J].软件学报.2003,14(4):804-810.
[6]徐成华,王蕴红,谭铁牛.三维人脸建模与应用[J].中国图象图形学报.2004,9(8):893-903.
[7]Lee S Y,Chwa K Y,Shin S Y.Image metamorphosis using snakes and free-form deformations[C].Proceedings of the 22nd annual conference on Computer graphics and interactive techniques,1995:439-448.
[8]Xu C,Quan L,Wang Y.Adaptive multi-resolution fitting and its application to realistic head modeling[C].Geometric Modeling and Processing,Beijing,China,2004:345-348.
[9]胡永利,尹宝才,程世铨.创建中国人三维人脸库关键技术研究[J].计算机研究与发展.2005,42(4):622-628.
[10]Zha H,Wang P.Realistic Face Modeling by Registration of 3-D Mesh Models and Multi-View Color Images[C].Proceeding of the 8th Int Conf Computer Aided Design and Computer Graphics,Oct.28-31,2003,Macao,China,2003:217-222.
[11]Lee Y,Terzopoulos D,Walters K.Realistic modeling for facial animation[C].In SIGGRAPH'95 Conference Proceedings:ACM press,Los Angels,1995:55-62.
[12]刘晓宁.基于三维模型的人脸识别技术研究[D].博士学位论文.西北工业大学,2006.
[13]Waters K,Terzopoulos D.Modeling and animating faces using scanned data[J].Visualization and Computer Animation.1991,2(4):123-128.
[14]Posdamer J L,Altschuler M D.Surface measurement by space-encoded projected beam systems[J].Computer Graphics and Image Processing.1982,18(1):1-17.
[15]Beumier C,Acheroy M.3D facial surface acquisition by structured light[C].International Workshop on Synthetic-Natural Hybrid Coding and Three Dimensional Imaging,Santorini,Greece,1999:103-106.
[16]Debevec P,Hawkins T,Tchou C.Acquiring the Reflectance Field of a Human Face[C].SIGGRAPH 2000 Conference,New Orleans,2000:145-156.
[17]Tarini M,Yamauchi H,Haber J.Texturing Faces[C].Graphics Interface 2002 Conference,Calgary,Canada,2002:89-98.
[18]Ikeuchi K,Horn B K P.Numerical shape from shading and occluding boundaries[M].Shape from shading,MIT Press,1989,245-299.
[19]Blake A,Zimmerman A,Knowles G.Surface descriptions from stereo and shading[J].Image and Vision Computing.1986,3(4):183-191.
[20]Pentland A P.Local shading analysis[M].Shape from shading,MIT Press,1989,443-487.
[21]Pentland A.Shape Information From Shading:A Theory About Human Perception[C].Second International Conference on Computer Vision,Florida,USA,1988:404-413.
[22]Samaras D,Metaxas D.Incorporating Illumination Constraints in Deformable Models for Shape from Shading and Light Direction Estimation[J].IEEE Trans.PAMI.2003,25(2):247-264.
[23]Zhao W Y,Chellappa R.Symmetric Shape-from-Shading Using Self-ratio Image[J].Int.J.Comput.Vision.2001,45(1):55-75.
[24]Smith W A P,Hancock E R.Recovering Facial Shape Using a Statistical Model of Surface Normal Direction[J].IEEE Trans.PAMI.2006,28(12):1914-1930.
[25]王琨,郑南宁.基于SFM算法的三维人脸模型重建[J].计算机学报.2005,28(6):1048-1053.
[26]Sengupta K,Ko C C.Scanning face models with desktop cameras[J].IEEE Transactions on Industrial Electronics.2001,48(5):904-912.
[27]沈晔湖,刘济林.利用立体图对的三维人脸模型重建算法[J].计算机辅助设计与图形学学报.2006,18(12):1904-1910.
[28]Pighin F,Hecker J,Lischinski D.Synthesizing realistic facial expressions from photographs[C].Proceedings of the 25th annual conference on Computer graphics and interactive techniques,1998:75-84.
[29]Dimitrijevic M,Ilic S F P.Accurate face models from uncalibrated and ill-lit video sequence[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Jun 27-Jul 2,2004,Washington,DC,USA,2004:188-202.
[30]Liu Z,Zhang Z,Chuck J.Rapid modeling of animated faces from video[J]. The Journal of Visualization and Computer Animation.2001,12(4):227-240.
[31]Shan Y,Liu Z,Zhang Z.Model-based Bundle Adjustment with Application to Face Modeling[C].Eighth IEEE International Conference on Computer Vision,Vancouver,BC,Canada,2001:644-651.
[32]梁荻,苏志勋.基于正交照片的人脸重建技术[J].系统仿真学报.2003,15(11):1646-1650.
[33]晏洁,高文,尹宝才.具有真实感的三维虚拟特定人脸生成方法[J].计算机学报.1999,22(2):147-153.
[34]梅丽,鲍虎军,彭群生.特定人脸的快速定制和肌肉驱动的表情动画[J].计算机辅助设计与图形学学报.2001,13(12):1077-1082.
[35]王鑫,孙守迁,陈廓.基于区域控制模型的三维人脸重建技术[J].计算机辅助设计与图形学学报.2007,119(18):1046-1050.
[36]高鹏,东彭翔,田劲东.三维人脸建模中面部特征轮廓线的提取[J].系统仿真学报.2006,18(8):2105-2113.
[37]彭翔,高鹏东,刘晓利.真实感人脸模型的细分曲面重建[J].计算机辅助设计与图形学学报.2006,18(5):744-747.
[38]魏诗国.素描[M].北京:高等教育出版社,1999.
[39]Rudomin I,Bojorquez A,Cuevas H.Statistical Generation of 3D Facial Animable Models[C].Proceedings of the Shape Modeling International 2002,2002:219.
[40]Iwasa T,Shima T,Sai M.3D Eigenfaces for face modeling[C].Proceedings 5th Asian Conference on Computer Vision,2002:1-6.
[41]Blanz V,Vetter T.A morphable model for the synthesis of 3D faces[C].Proceedings of the 26th annual conference on Computer graphics and interactive techniques,1999:187-194.
[42]Ullman S,Basri R.Recognition by Linear Combination of Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1991,13(10):992-1006.
[43]Shashua A.Projective Structure from two Uncalibrated Images:Structure from Motion and Recognition[R].Massachusetts Institute of Technology,1992.
[44]Poggio T,Vetter T.Recognition and Structure from one 2D Model View:Observations on Prototypes,Object Classes and Symmetries[R].Massachusetts Institute of Technology,1992.
[45]Vetter T,Poggio T.Linear object classes and image synthesis from a single example image[J].IEEE Trans.PAMI.1997,19(7):733-742.
[46]Blanz V,Basso C,Poggio T.Reanimating Faces in Images and Video[C].EUROGRAPHICS,Granada,Spain,2003:641-650.
[47]Blanz V,Vetter T.Face recognition based on fitting a 3D morphable model[J].IEEE Trans.PAMI.2003,25(9):1063-1074.
[48]Blanz V,Grother P,Phillips P J.Face recognition based on frontal views generated from non-frontal images[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:454-461.
[49]Romdhani S.Face image analysis using a multiple feature fitting strategy[D].Ph.D.thesis.Basel,Switzerland:University of Basel,,2005.
[50]胡永利,尹宝才,谷春亮.基于形变模型的三维人脸重建方法及其改进[J].计算机学报.2005,28(10):1671-1679.
[51]胡永利.真实感三维人脸建模及应用研究[D].博士学位论文.北京工业大学,2004.
[52]王成章,尹宝才,孙艳丰.改进的基于形变模型的三维人脸建模方法[J].自动化学报.2007,33(3):232-239.
[53]谷春亮,尹宝才,孔德慧.基于三维多分辨率模型与Fisher线性判别的人脸识别方法[J].计算机学报.2005,25(1):97-104.
[54]Basri R,Jacobs D W.Lambertian Reflectance and Linear Sub-spaces[J].IEEE Trans.PAMI.2003,25(2):218-233.
[55]郑南宁,付昀,张婷.人脸的表情与年龄变换和非完整信息的重构技术(上)[J].电子学报.2003,31(12A):1955-1962.
[56]付昀,郑南宁,张婷.人脸的表情与年龄变换和非完整信息的重构技术(下)[J].电子学报.2003,31(12A):1963-1970.
[57]Fu Y,Zheng N.M-Face:An Appearance-Based Photorealistic Model for Multiple Facial Attributes[J].IEEE Trans.CSVT.2006,16(7):830-842.
[58]裴玉茹,查红彬.真实感人脸的形状与表情空间[J].计算机辅助设计与图形学学报.2006,18(5):613-619.
[59]Amberg B,Blake A,Fitzgibbon A.Reconstructing High Quality Face-Surfaces using Model Based Stereo[C].IEEE 11th International Conference on Computer Vision,2007,Rio de Janeiro,Brazil,2007:1-8.
[60]Blanz V,Mehl A,Vetter T.A statistical method for robust 3D surface reconstruction from sparse data[C].2nd International Symposium on 3D Data Processing,Visualization,Thessaloniki,Greece,2004:293-300.
[61]Jiang D,Hu Y,Yan S.Efficient 3D reconstruction for face recognition[J].Pattern Recognition.2005,38(6):787-798.
[62]Knothe R,Romdhani S,Vetter T.Combining PCA and LFA for Surface Reconstruction from a Sparse Set of Control Points[C].7th International Conference on Automatic Face and Gesture Recognition,2006:637-644.
[63]Parke F I.A model for human faces that allows speech synchronized animation[C].The 1st annual conference on Computer graphics and interactive techniques,Boulder,Colorado,1974:2.
[64] Parke F I. Parameterized Models for Facial Animation[J]. IEEE Comput.Graph.Appl. 1982, 2(9): 61-68.
[65] Parke F, Waters K. Computer Facial Animation[M]. Wellesley, MA: A. K.Peters, 1996.
[66] Ekman P, Friesen W V. Manual for the facial action coding system[M].Palo Alto: Consulting Psychologists Press, 1977.
[67] Platt S M, Badler N I. Animating facial expressions[J]. SIGGRAPH Comput. Graph. 1981, 15(3): 245-252.
[68] Waters K. A muscle model for animation three-dimensional facial expression[C]. International Conference on Computer Graphics and Interactive Techniques, 1987: 17-24.
[69] Thalmann N, Primeau N, Thalmann D. Abstract muscle action procedures for human face animation[J]. Visual Computer. 1988, 3(5): 290-297.
[70] Thalmann N M, Cazedevals A, Thalmann D. Modelling Facial Communication between an Animator and a Synthetic Actor in Real Time[C].Modeling in Computer Graphics, Genova, Italy, 1993: 387-396.
[71] Sederberg T W, Parry S R. Free-form deformation of solid geometric models[J]. SIGGRAPH Comput. Graph. 1986, 20(4): 151-160.
[72] Coquillart S. Extended free-form deformation: a sculpturing tool for 3D geometric modeling[C]. 17th annual conference on Computer graphics and interactive techniques, Dallas, TX, USA, 1990: 187-196.
[73] Wang C L Y, Forsey D R. Langwidere: a new facial animation system[C].Proceedings of Computer Animation apos, Geneva,Switzerland, 1994: 59-68.
[74] Tony D, Michael K, Truong T. Subdivision surfaces in character animation[C]. International Conference on Computer Graphics and Interactive Techniques, 1998: 85-94.
[75] Reeves W. Simple and complex facial animation: Case studies[C].SIGGRAPH'90, 1990:88-106.
[76] Eisert P, Girod B. Analyzing Facial Expressions for Virtual Conferencing[J]. IEEE Comput. Graph. Appl. 1998, 18(5): 70-78.
[77] Cootes T F, Edwards G J, Taylor C J. Active appearance models[J]. IEEE Trans. PAMI. 2001, 23(6): 681-685.
[78] Vetter T, Romdhani S. Face Modelling and Recognition Tutorial (2)[C].The 8th European Conference on Computer Vision, Prague , Czech, 2004.
[79] The BJUT-3D Large-Scale Chinese Face Database, Technical Report No ISKL-TR-05-FMFR-001, Multimedia Tech & Graphic Lab, Beijing University of Technology[R]. http://www.bjut.edu.cn/sci/multimedia/mul-1ab/3dface/,2005.
[80] Vetter T, Blanz V. Estimating coloured 3d face models from single images:An example based approach[C]. European Conference on Computer Vision'98,Freiburg, Germany, 1998: 499-513.
[81] Vetter T, Jones M J, Poggio T. A bootstrapping algorithm for learning linear models of object classes[C]. IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico,USA, 1997: 40-47.
[82] Gu C, Yin B, Hu Y. Resampling Based Method for Pixel-wise Correspondence between 3D Faces[C]. International Conference on Information Technology: Coding and Computing, 2004: 614-619.
[83] 尹宝才,何晏晏,孙艳丰.三维人脸的非均匀重采样对齐算法[J].北京工业大学学报. 2007, 33(2): 213-218.
[84] Farkas L G. Anthropometry of the Head and Face, 2nd edition[M]. New York: Raven Press, 1994.
[85] Sobottka K, Pitas I. A Fully Automatic Approach to Facial Feature Detection and Tracking[C]. The First International Conference on Audio- and Video-Based Biometric Person Authentication, 1997: 77-84.
[86] Garland M, Heckbert P S. Surface simplification using quadric error metrics[C]. Computer Graphics Proceedings (SIGGRAPH 97), 1997: 209-216.
[87] Romdhani S, Vetter T. Efficient, Robust and Accurate Fitting of a 3D Morphable Model[C]. Ninth IEEE International Conference on Computer Vision - Volume 2, 2003: 59-66.
[88] Blanz V, Vetter T. Reconstructing the complete 3D shape of faces from partial information[J]. Informationsetechnik und Technische Informatik. 2002,44(6): 295-302.
[89] Moccozet L, Thalmann N M. Dirichlet Free-Form Deformations and their Application to Hand Simulation[C]. Proceedings of the Computer Animation,1997: 93-102.
[90] Penev P S, Atick J J. Local Feature Analysis: A general statistical theory for object representation[J]. Network: Computation in Neural Systems. 1996,7(3): 477-500.
[91] Cootes T F, Taylor C J, Cooper D H. Active shape models\—their training and application[J]. Comput. Vis. Image Underst. 1995, 61(1): 38-59.
[92] Turk M, Pentland A. Eigenfaces for recognition[J]. J. Cognitive Neuroscience. 1991, 3(1): 71-86.
[93] Duda R O, Hart P E, Stork D G. Pattern Classification(2nd Edition)[M].Wiley-Interscience, 2000: 680.
[94] Gong X, Wang G. Realistic face modeling based on multiple deformations[J]. The Journal of China Universities of Posts and Telecommunications. 2007, 14(4): 110-117.
[95] Gong X, Wang G. A Dynamic Component Deforming Model for Face Shape Reconstruction[C]. International Symposium on Visual Computing 2007,Lake Tahoe, NV, United States, 2007: 488-497.
[96] Lee W, Magnenat-thalmann N. Fast head modeling for animation[J]. Image and Vision Computing. 2000, 18(4): 355-364.
[97] 王鹏.三维人脸建模中的纹理映射研究[D].硕士.北京:北京大学,2004.
[98] Gong X, Wang G. An automatic approach for pixel-wise correspondence between 3D faces[C]. International Conference on Hybrid Information Technology, Cheju Island, Korea, 2006: 198-205.
[99] Criminisi A, Perez P, Toyama K. Object removal by exemplar-based inpainting[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C], Wisconsin, USA, 2003: 18-20.
[100] Gao W, Cao B, Shan S. The CAS-PEAL Large-Scale Chinese Face Database and Evaluation Protocols[R]. Technical Report No.JDL_TR_04_FR_001, Joint Research & Development Laboratory, CAS, 2004.
[101] Chan H, Bledsoe W W. A man-machine facial recognition system: some preliminary results[R]. Panoramic Research, 1965.
[102] Philips P J, Grother P J, Micheals R J. Face Recognition Vendor Test 2002:Evaluation report[R]. National Institute of Standards and Technology, 2003.
[103] Eriksson, Weber D. Towards 3-dimensional face recognition[C]. In 5th IEEE AFRICON, 1999: 401-406.
[104] Verier T, Poggio T. Linear object classes and image synthesis from a single example image[J]. IEEE Trans. PAMI. 1997, 19(7): 733-741.
[105] Adinl Y, Mcees Y, Ullman S. Face recognition: the problem of compensating for changes in illumination direction[J]. IEEE Trans. PAMI.1997, 19(7): 721-732.
[106] Moghaddara B. Principal manifolds and probabilistic subspaces for visual recognition[J]. IEEE Trans. PAMI. 2002, 24(6): 708-788.
[107] Basria R, Jacobs D. Lambertian reflectance and linear subspaees[J]. IEEE Trans. PAMI. 2003, 25(2): 218-233.
[108] Hallinan P. A low-dimensional representation of human faces for arbitrary lighting conditions[C]. CVPR'94, Seattle Washington, 1994: 995-999.
[109] Basria R, Jacobs D. Lambertian reflectance and linear subspaces[C].ICCV'01, Vancouver,Canada, 2001: 383-390.
[110] Ramamoorthi R. Analytic PCA construction for theoretical analysis of lighting variability in Images of a lambertian object[J]. IEEE Trans. on PAMI. 2002,24(10):1-12.
[111]Georghiades A S,Belhumeur P N,Kriegrnan D J.From few to many illumination cone models for face recognition under differing pose and lighting[J].IEEE Trans.PAMI.2001,23(6):643-660.
[112]Sim T,Kanade T.Combining models and exemplars for face recognition:an illuminating example[C].Workshop on Models versus Exemplars in Computer Vision with CVPR01,2001:47-56.
[113]Lee K C,Ho J,Kreigman D.Nine points of light:acquiring subspaces for face recognition under variable lighting[C].CVPR'01,Kauai,Hawaii,2001:519-526.
[114]Zhang L,Samaras D.Face recognition under variable lighting using harmonic image exemplars[C].CVPR'03,Madison,Wisconsin,2003:19-25.
[115]卿来云,山世光,高文.基于球面谐波基图像的任意光照下的人脸识别[J].计算机学报.2006,29(5):760-768.
[116]Chen Q,Wu H,Fukumoto T.3D head pose estimation without feature tracking[C].The Third IEEE International Conference on Automatic Face and Gesture Recognition,Nara,1998:88-93.
[117]叶航军,白雪生,徐光.基于支持向量机的人脸姿态判定[J].清华大学学报.2003,43(1):67-70.
[118]Nikolaidis A,Pitas I.Facial feature extraction and determination of pose[J].Pattern Recognition.2000,33(11):1783-1791.
[119]梁国远,查红彬,刘宏.基于三维模型和仿射对应原理的人脸姿态估计方法[J].计算机学报.2005,28(5):792-799.
[120]Lopez R,Huang T S.3D Head pose computation from 2D images:template versus features[C].IEEE International Conference on Image Processing,Singapore,1995:599-602.
[121]Shimizu I,Zhang Z,Akamatsu S.Head pose determination from one image using a genetic model[C].IEEE International Conference on Automatic Face and Gesture Recognition,Nara,1998:100-105.
[122]Yang R,Zhang Z.Model-based head pose tracking with stereo vision[C].IEEE International Conference on Automatic Face and Gesture Recognition,2002:255-260.
[123]Georghiades A S,Belhumeur P N,Kriegman D J.From Few to Many:Illumination Cone Models for Face Recognition under Variable Lighting and Pose[J].IEEE Trans.PAMI.2001,23(6):643-660.
[124]Yao P,Evans G,Calway A.Using affine correspondence to estimate 3-D facial pose[C].IEEE International Conference on Image Processing,2001:919-922.
[125]Arai K,Kurihara T,Anjyo K.Bilinear interpolation for facial expression and metamorhposis in real-time animation[J].The Visual Computer.1996,12(3):105-116.
[126]Cohen M,Massara D.Modeling co-articulation in synthetic visual speech[C].Model and Technique in Computer Animation,Tokyo,1993:139-156.
[127]姜大龙,王兆其,高文.基于MPEG-4的三维人脸动画实现方法[J].系统仿真学报.2001(s2):493-496.
[128]姜大龙,高文,王兆其.面向纹理特征的真实感三维人脸动画方法[J].计算机学报.2004,27(6):750-757.
[129]王奎武,王洵,董兰芳.一个MPEG4兼容的人脸动画系统[J].计算机研究与发展.2001,38(5):529-535.
[130]Hu Y,Yin B,Sun Y.3D Face Animation Based on Morphable Model[J].Journal of Information & Computational Science.2005,2(1):35-39.
[131]王成章,尹宝才,白晓明.一种兼容于MPEG-4的三维人脸动画[J].北京工业大学学报.2007,33(10):1102-1106.
[132]Lang C.Kriging Interpolation[R].http://www.nbb.cornell.edu/neurobio/land/OldStudentProjects/cs490-94to95/clang/kriging.html,1998.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |