基于形变模型的三维人脸建模方法研究
|
摘要
人脸是人们日常生活中信息交流和情感表达最重要的载体。通过人脸，我们不仅可以获取一个人的身份、种族信息，还可以获取对方当前的情感状态。随着计算机视觉技术的不断发展，人们对自然、便捷的人机交互技术的要求不断提高，真实感三维人脸建模技术作为人机交互技术中最重要的组成部分自然成为研究的热点。目前，三维人脸建模技术已经取得了长足的发展，并被广泛的应用于影视动画、游戏娱乐、人机交互、医疗技术、辅助教学等诸多领域。
传统的三维人脸建模方法在模型的建立效果和建模过程的自动化等方面还存在着很大的不足。基于形变模型的三维人脸建模方法是目前建模效果最好的方法之一，该方法是基于统计学习理论建立的。与其它的建模方法相比，该方法在建模效果、建模过程的自动化程度等方面都有比较好的表现。本文的研究工作围绕基于形变模型的三维人脸建模方法展开，针对形变模型方法存在的不足和问题进行了深入探讨和研究。本文的研究内容主要包括以下几个方面。
1、基于组合模型匹配的样本规格化
规格化三维人脸样本集是建立形变模型的关键前提。由于建库目的和采集方法的不同，不同数据库中的三维人脸样本在拓扑结构、数据形式、信息含量上有着很大的差异。为了能够在不同人脸样本之间实施线性运算，需要对初始三维人脸样本进行规格化处理，使得这些样本具有相同的拓扑结构和点面信息，并可以使用统一的向量形式进行表示。本文在深入分析三维人脸样本结构特性的基础之上提出了基于组合模型匹配的三维人脸样本规格化方法。该方法首先基于规格化样本集建立三维人脸组合模型，然后通过将组合模型与目标样本进行匹配的方式实现样本规格化。由于组合模型是建立在规格化样本集上的统计模型，所以基于组合模型匹配得到的规格化样本不仅可以满足几何的约束，还可以满足人脸的合理性约束。
2、基于遗传算法的三维人脸样本扩充
三维人脸样本是三维人脸研究进行算法设计、模型训练以及性能比较所不可缺少的数据资源。由于受采集设备和条件的限制，目前的三维人脸数据库的数据规模都很小，样本的覆盖范围相对不足。为了解决这个问题，本文提出了一种基于已有的三维人脸样本集，通过遗传算法进行样本扩充的方法。该方法的基本思想是将三维人脸样本看作由有限固定器官组成的对象，利用遗传算法可以引导搜索进行的特点，通过选择、交叉、变异等操作将各样本的不同器官重新组合在一起来产生新的三维人脸样本。使用该方法不但可以产生大量的三维人脸样本，还可以增大样本集所涵盖的变化范围，大大增强现有样本集的可用性。
3、基于典型相关性分析的三维人脸建模
形变模型的假设前提是人脸空间是一个线性子空间，然而研究表明人脸是嵌套在高维空间当中的一个非线性流形。基于形变模型的建模方法必定会忽略人脸的某些细节特征，从而使得该方法难以得到更好的建模效果。为了进一步提高该方法的建模精度，本文提出了一种非线性三维人脸建模方法。该方法的基本思想是使用分段线性的方法来解决形变模型的线性假设前提和人脸的非线性特性之间的矛盾。该方法以典型相关性分析方法为基础，通过计算二维人脸图像与三维人脸样本之间的相关性来计算二者之间的距离，并以此为基础得到与输入图像相关的三维人脸样本集。在进行三维人脸建模时，首先基于这组样本集建立形变模型，并通过将形变模型与输入图像进行匹配的方式得到三维人脸建模结果。由于该模型是建立在与输入图像相关的三维人脸样本集之上，因此使用该模型可以对输入图像进行更好的表示。所以基于典型相关性分析的三维人脸建模方法可以进一步提高形变模型方法的建模精度。
4、基于粒子群优化算法的模型匹配
基于形变模型的三维人脸建模过程就是形变模型的匹配过程。由于在匹配求解过程中涉及到形状、纹理、摄像机和光照等一系列参数的求解，所以形变模型的匹配问题是一个大规模、多参数的优化问题。对该问题进行优化求解时，会遇到计算复杂度高、计算时间长和容易陷入局部极值点等问题。粒子群优化算法是一种基于群体智能的随机优化算法，该算法具有高度并行、易于实现等特点。本文在深入分析形变模型匹配特点的基础上，提出了基于粒子群优化算法的多层次模型匹配算法，进一步提高了模型匹配的速度和效率。由于粒子群优化算法是一种有信息反馈的随机优化算法，该方法对模型匹配问题具有很高的鲁棒性且对初值不敏感，因此使用本文提出的模型匹配算法可以极大地提高形变模型的匹配速度和匹配精度。
As the most important carrier for information exchange and emotion expressingin daily life, human face has been the focus of research and attention. Through face,we can not only obtain people’s identity and race information, but also can get hiscurrent emotion state. With the development of computer vision science, the demandsfor human-computer interaction technology grow much higher. As the most importantpart of human-computer interaction technology, realistic3D face modeling certainlybecomes the focus of research. At present,3D face modeling technology has beenmade a considerable progress, and has been widely used in many areas, such ascomputer games, virtual interaction, medical technology, and public safe.
Traditional3D face modeling methods have many deficiencies in modelingeffects and automatic modeling.3D face modeling method based on morphable modelis one of the best modeling at present. This method is constructed based on statisticallearning theory. Compared with other modeling methods, this method has betterperformance in modeling results and the automatic modeling.In this paper, theresearch works are carried out based on morphable model method and proposeappropriate solutions to corresponding flaws. The main works of this thesis areexamined in the following.
1. Sample regularization based on combination model matching
Regularized3D face sample set is an important precondition for constructingmorphable modeling. At present, samples in different3D face database have bigdifference in topology, data structure, information coverage due to the differentbuilding purpose and sample deriving method. In order to implement linear operationon different samples, these initial samples should be regularized first to have themwith same topology, number of point and area, and can be expressed by a uniformvector. After in-depth study of face structure, a regularization method based oncombination model matching has been proposed in this paper. The combination modelis constructed based on regularized sample set which are derived by handwork.Samples which need to be regularized are matched with the combination model to gettheir regularization result. Since the combination model is a statistical model based onregularized samples, the regularized sample derived based on this model not onlymeets the geometric constraints, but also meets the reasonable constraints for face.
2.3D face expansion based on Genetic Algorithm
3D face samples are indispensable data resource for algorithm design, modeltraining and performance comparison about3D face research. Due to the restrictions of sample equipment and condition, samples in current3D face database are few andthe coverage range is relative small. To solve this problem, we propose a sampleexpansion method based on genetic algorithm. The basic idea is that the3D facesamples consist of limited fixed organs and a lot of new samples can be generated byregrouping different organs from different samples. Using this method can not onlygenerate a lot of3D face samples, but also increase the range covered by the sampleset.
3.3D face modeling based on canonical correlation analysis
The assumption of the morphable model is that face space is a linear subspace.However, lots of studies show that human face is a nonlinear manifold embedded inhigh dimension space.3D face modeling method based on morphable model willcertainly ignore some details of face and affect the modeling results. In order tofurther improve the accuracy of modeling result, we proposed a nonlinear3D facemodeling method. The basic idea is to use the piecewise linear method to solve thecontradiction between the non-linear characteristics of face space and linearassumptions of the morphable model. This method is performed based on canonicalcorrelation analysis. The distance between2D face images and3D face samples arecalculated based on correlation distance and these correlative samples can be derivedin terms of this distance. When performing3D face modeling operation, a morphablemodel can be constructed based on these samples and the reconstructed sample can bederived by matching this model with input image. Since the model and input imageare highly correlated, a better reconstructed sample can be derived based on thismorphable model. Therefore,3D face modeling method based on canonicalcorrelation analysis can further improve modeling accuracy of morphable model.
4. Modeling matching based on particle swarm optimization
The process of3D face modeling based on morphable model is a matchingprocess. Due to the shape parameters, texture parameters, camera parameters andillumination parameters have been involved in matching process, the problem ofmorphable model matching is a large-scale and multi-parameters optimizationproblem. Particle Swarm Optimization is a swarm intelligence optimization algorithm,this algorithm is highly parallel and easy to implement. After in-depth study of thecharacteristics of modeling matching, a new multi-level modeling matching methodbased on particle swarm optimization to further improve the model matching speedand efficiency is proposed in this paper. Due to the particle swarm optimization is arandomly optimization algorithm with feedback, this method is robust to the matchingproblem of morphable model and sensitivity to the initial value. The proposed modelmatching algorithm used in this chapter can greatly improve the matching speed andmatching accuracy.
传统的三维人脸建模方法在模型的建立效果和建模过程的自动化等方面还存在着很大的不足。基于形变模型的三维人脸建模方法是目前建模效果最好的方法之一，该方法是基于统计学习理论建立的。与其它的建模方法相比，该方法在建模效果、建模过程的自动化程度等方面都有比较好的表现。本文的研究工作围绕基于形变模型的三维人脸建模方法展开，针对形变模型方法存在的不足和问题进行了深入探讨和研究。本文的研究内容主要包括以下几个方面。
1、基于组合模型匹配的样本规格化
规格化三维人脸样本集是建立形变模型的关键前提。由于建库目的和采集方法的不同，不同数据库中的三维人脸样本在拓扑结构、数据形式、信息含量上有着很大的差异。为了能够在不同人脸样本之间实施线性运算，需要对初始三维人脸样本进行规格化处理，使得这些样本具有相同的拓扑结构和点面信息，并可以使用统一的向量形式进行表示。本文在深入分析三维人脸样本结构特性的基础之上提出了基于组合模型匹配的三维人脸样本规格化方法。该方法首先基于规格化样本集建立三维人脸组合模型，然后通过将组合模型与目标样本进行匹配的方式实现样本规格化。由于组合模型是建立在规格化样本集上的统计模型，所以基于组合模型匹配得到的规格化样本不仅可以满足几何的约束，还可以满足人脸的合理性约束。
2、基于遗传算法的三维人脸样本扩充
三维人脸样本是三维人脸研究进行算法设计、模型训练以及性能比较所不可缺少的数据资源。由于受采集设备和条件的限制，目前的三维人脸数据库的数据规模都很小，样本的覆盖范围相对不足。为了解决这个问题，本文提出了一种基于已有的三维人脸样本集，通过遗传算法进行样本扩充的方法。该方法的基本思想是将三维人脸样本看作由有限固定器官组成的对象，利用遗传算法可以引导搜索进行的特点，通过选择、交叉、变异等操作将各样本的不同器官重新组合在一起来产生新的三维人脸样本。使用该方法不但可以产生大量的三维人脸样本，还可以增大样本集所涵盖的变化范围，大大增强现有样本集的可用性。
3、基于典型相关性分析的三维人脸建模
形变模型的假设前提是人脸空间是一个线性子空间，然而研究表明人脸是嵌套在高维空间当中的一个非线性流形。基于形变模型的建模方法必定会忽略人脸的某些细节特征，从而使得该方法难以得到更好的建模效果。为了进一步提高该方法的建模精度，本文提出了一种非线性三维人脸建模方法。该方法的基本思想是使用分段线性的方法来解决形变模型的线性假设前提和人脸的非线性特性之间的矛盾。该方法以典型相关性分析方法为基础，通过计算二维人脸图像与三维人脸样本之间的相关性来计算二者之间的距离，并以此为基础得到与输入图像相关的三维人脸样本集。在进行三维人脸建模时，首先基于这组样本集建立形变模型，并通过将形变模型与输入图像进行匹配的方式得到三维人脸建模结果。由于该模型是建立在与输入图像相关的三维人脸样本集之上，因此使用该模型可以对输入图像进行更好的表示。所以基于典型相关性分析的三维人脸建模方法可以进一步提高形变模型方法的建模精度。
4、基于粒子群优化算法的模型匹配
基于形变模型的三维人脸建模过程就是形变模型的匹配过程。由于在匹配求解过程中涉及到形状、纹理、摄像机和光照等一系列参数的求解，所以形变模型的匹配问题是一个大规模、多参数的优化问题。对该问题进行优化求解时，会遇到计算复杂度高、计算时间长和容易陷入局部极值点等问题。粒子群优化算法是一种基于群体智能的随机优化算法，该算法具有高度并行、易于实现等特点。本文在深入分析形变模型匹配特点的基础上，提出了基于粒子群优化算法的多层次模型匹配算法，进一步提高了模型匹配的速度和效率。由于粒子群优化算法是一种有信息反馈的随机优化算法，该方法对模型匹配问题具有很高的鲁棒性且对初值不敏感，因此使用本文提出的模型匹配算法可以极大地提高形变模型的匹配速度和匹配精度。
As the most important carrier for information exchange and emotion expressingin daily life, human face has been the focus of research and attention. Through face,we can not only obtain people’s identity and race information, but also can get hiscurrent emotion state. With the development of computer vision science, the demandsfor human-computer interaction technology grow much higher. As the most importantpart of human-computer interaction technology, realistic3D face modeling certainlybecomes the focus of research. At present,3D face modeling technology has beenmade a considerable progress, and has been widely used in many areas, such ascomputer games, virtual interaction, medical technology, and public safe.
Traditional3D face modeling methods have many deficiencies in modelingeffects and automatic modeling.3D face modeling method based on morphable modelis one of the best modeling at present. This method is constructed based on statisticallearning theory. Compared with other modeling methods, this method has betterperformance in modeling results and the automatic modeling.In this paper, theresearch works are carried out based on morphable model method and proposeappropriate solutions to corresponding flaws. The main works of this thesis areexamined in the following.
1. Sample regularization based on combination model matching
Regularized3D face sample set is an important precondition for constructingmorphable modeling. At present, samples in different3D face database have bigdifference in topology, data structure, information coverage due to the differentbuilding purpose and sample deriving method. In order to implement linear operationon different samples, these initial samples should be regularized first to have themwith same topology, number of point and area, and can be expressed by a uniformvector. After in-depth study of face structure, a regularization method based oncombination model matching has been proposed in this paper. The combination modelis constructed based on regularized sample set which are derived by handwork.Samples which need to be regularized are matched with the combination model to gettheir regularization result. Since the combination model is a statistical model based onregularized samples, the regularized sample derived based on this model not onlymeets the geometric constraints, but also meets the reasonable constraints for face.
2.3D face expansion based on Genetic Algorithm
3D face samples are indispensable data resource for algorithm design, modeltraining and performance comparison about3D face research. Due to the restrictions of sample equipment and condition, samples in current3D face database are few andthe coverage range is relative small. To solve this problem, we propose a sampleexpansion method based on genetic algorithm. The basic idea is that the3D facesamples consist of limited fixed organs and a lot of new samples can be generated byregrouping different organs from different samples. Using this method can not onlygenerate a lot of3D face samples, but also increase the range covered by the sampleset.
3.3D face modeling based on canonical correlation analysis
The assumption of the morphable model is that face space is a linear subspace.However, lots of studies show that human face is a nonlinear manifold embedded inhigh dimension space.3D face modeling method based on morphable model willcertainly ignore some details of face and affect the modeling results. In order tofurther improve the accuracy of modeling result, we proposed a nonlinear3D facemodeling method. The basic idea is to use the piecewise linear method to solve thecontradiction between the non-linear characteristics of face space and linearassumptions of the morphable model. This method is performed based on canonicalcorrelation analysis. The distance between2D face images and3D face samples arecalculated based on correlation distance and these correlative samples can be derivedin terms of this distance. When performing3D face modeling operation, a morphablemodel can be constructed based on these samples and the reconstructed sample can bederived by matching this model with input image. Since the model and input imageare highly correlated, a better reconstructed sample can be derived based on thismorphable model. Therefore,3D face modeling method based on canonicalcorrelation analysis can further improve modeling accuracy of morphable model.
4. Modeling matching based on particle swarm optimization
The process of3D face modeling based on morphable model is a matchingprocess. Due to the shape parameters, texture parameters, camera parameters andillumination parameters have been involved in matching process, the problem ofmorphable model matching is a large-scale and multi-parameters optimizationproblem. Particle Swarm Optimization is a swarm intelligence optimization algorithm,this algorithm is highly parallel and easy to implement. After in-depth study of thecharacteristics of modeling matching, a new multi-level modeling matching methodbased on particle swarm optimization to further improve the model matching speedand efficiency is proposed in this paper. Due to the particle swarm optimization is arandomly optimization algorithm with feedback, this method is robust to the matchingproblem of morphable model and sensitivity to the initial value. The proposed modelmatching algorithm used in this chapter can greatly improve the matching speed andmatching accuracy.
引文
[1] Parke F I, Waters K. Computer Facial Animation [J]. Wellesley, Massachusetts,1996.
[2] Pighin F, Hecker J, Lischinski D, Szeliski R, Salesin D H. Synthesizing realisticfacial expressions from photographs [C]. Proceedings of SIGGRAPH,1998:75-84.
[3] Mehrabian A. Communication without words [J]. Psychology Today,1968,2(4):53-56.
[4] Parke F I. Parameterized models for facial animation[C]. IEEE ComputerGraphics and Applications,1982,2(9):61-68
[5] Parke F I. A model for human faces that allows speech synchronizedanimation[J]. Journal of Computers and Graphics,1975,1(1):1-4.
[6] Parke F I. Parameterized models for facial animation[C]. IEEE ComputerGraphics,1982,2(9):61-68.
[7] Parke F I. Control Parameterization for facial animation[J], ComputerAnimation, Tokyo: Springer-Verlag,1991:3-13.
[8] Parke F I, Waters K. Computer Facial Animation[J], AK Peters,1994.
[9] Pighin F, Auslander J, Lischinski D, et al. Realistic facial animation using imagebased3D morphing[J]. Technical Report TR-97-01-03, University ofWashington, Computer Science Department, January1997.
[10] Pighin F. Modeling and animating realistic faces from images[D]. Ph. Ddissertation, University of Washington,1999.
[11] Lee W S, Escher M, Sannier G, Magnenat-Thalmann N. MPEG-4CompatibleFaces from Orthogonal Photos[C]. International Conference on ComputerAnimation, Geneva, Switzerland,1999:186-194.
[12] Lee W S, Kalra P, Magnenat-Thalmann N. Model Based Face Reconstructionfor Animation[C]. Proceeding of Multimedia Modeling, Singapore,1997,323-338.
[13] Lee W S, Magnenat-Thalmann N. Fast Head Modeling for Animation[J].Journal Image and Vision Computing,2000,18(4):355-364.
[14] Liu Z C, Shan Y, Zhang Z.Y. Expressive expression mapping with ratioimages[C]. Proceedings of SIGGRAPH’01,2001:71-276.
[15] Liu Z C, Zhang Z Y, Jacobs C., Cohen M. Rapid modeling of animated facesfrom video images[C]. ACM Multimedia,2000:475-476.
[16] Horace H S., Yin L J. Constructing a3D Individualized Head Model from TwoOrthogonal Views[J]. The Visual Computer,1996,12:254-266.
[17] Akimoto T, Suenaga Y, and Wallace R S. Automatic Creation of3D FacialModels[J]. IEEE Computer Graphics and Applications,1993,13(4):16–22.
[18] Horn B, Obtaining shape from shading information[C]. In P. Winston, editor,The Psychology of Computer Vision. McGraw-Hill, New York,1975.
[19] Horn B, Brooks M, Shape from Shading. The MIT Press,1989.
[20] CATTELAN M, HANCOCK E R. Acquiring height maps of faces from a singleimage[C], Proceedings of the2nd International Symposium on3D DataProcessing, Visualization and Transmission,2004:183-190
[21] CATTELAN M, HANCOCK E R. Acquiring height data from a single image ofa face using local shape indicators[J], Computer Vision and ImageUnderstanding,2006,103(1):64-79.
[22] SMITH W A P, HANCOCK E R. Recovering facial shape and albedo using astatistical model of surface normal direction[C]. IEEE International Conferenceon Computer vision.2005:588-595
[23] Zhao W, Chellappa R. Symmetric shape-from-shading using self-ratio image[J].International Journal of Computer Vision,2001:55–75.
[24] Prados E, Camilli F, and Faugeras O. A unifying and rigorous shape fromshading method adapted to realistic data and applications[J]. J. Math. ImagingVis.,2006,25(3):307–328.
[25] Prados E, Faugeras O. Shape from shading: a well-posed problem?[C]. IEEEConference on Computer Vision and Pattern Recognition.2005,2:870–877.
[26] Kemelmacher I, Basri R. Molding face shapes by example[C]. EuropeonConference on Computer Vision,2006:277–288.
[27] Dovgard R, Basri R. Statistical symmetric shape from shading for3d structurerecovery of faces[C]. Proceedings of the European Conference on ComputerVision,2004:108–116.
[28] Jollife I T. Principal Component Analysis[J]. Springer-Verlag, New York,1986.
[29] Atick J J, Griffin P A, Redlich A N. Statistical approach to shape from shading:Reconstruction of3d face surfaces from single2d images[J]. NeuralComputation,1996,8:1321–1340.
[30] Smith W A P, Hancock E R. Recovering facial shape and albedo using astatistical model of surface normal direction[C]. IEEE International Conferenceon Computer Vision,2005:588–595.
[31] Blanz V, Vetter T. A morphable model for the synthesis of3D faces[C].Proceedings of SIGGRAPH’99,1999:187–194.
[32] Ullman S, Basri R. Recognition by Linear Combinations of Models[J]. A.I.Memo1152, MIT Artificial Intelligence Laboratory, Cambridge, MA, USA,1989.
[33] Shashua A. Projective structure from two uncalibrated images: Structure frommotion and recognition[J]. A.I. Memo1363, MIT,1992.
[34] Choi C S., Okazakit T, Harashima H., Takebe T. A system of analyzing andsynthesizing facial images[C]. In Proc. IEEE International Conference onSymposium of Circuit and Syatems,1991:2665–2668.
[35] Poggio T, Brunelli R. A novel approach to graphics[J]. A.I. Memo1354, MIT,1992
[36] Poggio T., Vetter T. Recognition and Structure from one2D Model View:Observations on Prototypes[J], Object Classes and Symmetries. A.I. Memo1354, MIT,1992.
[37] Vetter T, Poggio T. Linear objects classes and image synthesis from a singleexample image[J]. A.I. Memo1531, MIT,1995.
[38] Jones M J, Poggio T. Model-based matching by linear combinations ofprototypes[J]. A.I. Memo1583, MIT,1996.
[39] Vetter T, Blanz V. Estimating coloured3d face models from single images: Anexample based approach[C]. European Conference on Computer VisionFreiburg,1998:499-513.
[40]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.
[41]晏洁,高文.基于一般人脸模型修改的特定人脸合成技术[J]，计算机辅助设计与图形学,1999,11(5):389-394.
[42] Gao W, Chen Y Q, Wang R, Shan S G, Jiang D L. Learning and SynthesizingMPEG-4Compatible3-D Face Animation from Video Sequence[J]. IEEETransactions on Circuits and Systems for Video technology.2003,13(11):1119-1128.
[43]陈益强,高文,王兆其,姜大龙.基于机器学习的语音驱动人脸动画方法[J].软件学报,2003,14(2):215-221.
[44] Shan S G., Gao W, Yan B, et al. Individual3Dface synthesis based onorthogonal photos and speech-driven facial animation[C].2000InternationalConference on Image Processing,2000,1(3):238-241.
[45]梅丽,鲍虎军.基于实拍图像的人脸真实感重建[J].计算机学报,2000,23（9）:996-1002
[46]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.
[47]张青山,陈国良.具有真实感的三维人脸动画[J].软件学报,2003,14(3):643-650.
[48]张翔宇,华蓓,陈意云.人脸建模和动画的基本技术[J].计算机辅助设计与图形学学报，2001,13(4):343-347.
[49]王奎武,王询,董兰芳,陈意云.一个MPEG一兼容的人脸动画系统[J].计算机研究与发展.2001,38(5):529-535.
[50] Chen T B, Yin B C, Huang W J, and Kong D H. Animating Human Face underArbitrary Illumination[C]. In Proceedings of Pacific Graphics'01, Tokyo, Japan,2001:314-321.
[51]尹宝才,胡永利,程世铨,谷春亮.基于形变模型的人脸建模及其应用综述[J].北京工业大学学报,2003,29(3):364-371.
[52]尹宝才,孙艳丰,王成章,盖赟. BJUT-3D三维人脸数据库及其处理技术[J].计算机研究与发展.2009,46(6):1009-1018.
[53]胡永利,尹宝才,程世锉,谷春亮,刘文韬.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.
[54] Hu Y L, Yin B C, Sun Y F, Cheng S Q.3D Face Animation Based on MorphableModel[J]. Journal of Information and Computational Science,2005,2(1):35-40.
[55] Hu Y L, Yin B C, Kong D H, A new facial feature extraction method based onlinear combination model[C], Proceedings IEEE/WIC International Conferenceon Web Intelligence,2003:520-523.
[56] Hu Y L, Yin B C, Cheng S Q, Gu C.L, A3D facial combination model based onmesh resampling[C], International Conference on Signal ProcessingProceedings,2004:1231-1234.
[57] Hu Y L, Yin B C, Sun Y F. Multi-lighting3D face morphable model based onmesh resampling[C].2005IEEE International Conference on Acoustics, Speech,and Signal Processing (IEEE Cat. No.05CH37625),2005,1121-1124.
[58] Hu Y L, Yin B C, Cheng S Q, Gu C L. An Improved Morphable Model For3DFace Synthesis[C]. The Third International Conference on Machine Learningand Cybernetics.2004:26-29.
[59] Wang C Z, Yin B C, Shi Q, Sun Y F.3D Face Correspondence Based onUniform Mesh Resampling Combined with Mesh Simplification[J], Journal ofComputational Information Systems,2005,1(2):343-350.
[60] Yin B C, Wang C Z, Shi Q, Sun Y F. MPEG-4Compatible3D Facial AnimationBased on Morphable Model[C], Proceedings of the Fourth InternationalConference on Machine Learning and Cybernetics, Guangzhou,2005:4936-4941.
[61] Wang C Z, Yin B C, Shi Q, Sun Y F. An improved3D face synthesis based onmorphable model[C],2nd International Conference on Artificial IntelligenceApplications and Innovations, ARTIFICAL INTELLIGENCE APPLICATIONSAND INNOVATIONS II:2005:183-187,ISTP）
[62] Wang C Z, Yin B C, Bai X M, Sun Y F. Improved Genetic Algorithm BasedModel Matching Method for3D Face Synthesis[C], International Symposiumon Computing and Its Application in Information Science,2005:381-384.
[63] Yin B C, Wang C Z, Shi Q, Sun Y F, Morphable Model Based FacialAnimation[C]. International Symposium on Computing and Its Application inInformation Science,2005:291-295.
[64]王成章,石勤,孙艳丰,尹宝才,三维人脸纹理改善及其在模型匹配中的应用[J],北京工业大学学报，2006,32(3):246-251.
[65]王成章,尹宝才,石勤,孙艳丰,基于形变模型的真实感三维人脸动画研究,计算机工程与应用[J],2006,42(6):33-35.
[66]王成章,尹宝才,孙艳丰,胡永利.一种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.
[67] Gu C L, Yin B C, Hu Y L, Cheng S Q. Resampling based method for pixel-wisecorrespondence between3D faces[C], International Conference on InformationTechnology: Coding and Computing,2004:614-619.
[68] Wu S N, Yin B C, Cai T. The synthesis of realistic human face[C]. ThirdInternational Conference on Advances in Multimodal Interfaces-ICMI,2000,1948:199-206.
[69]胡永利,真实感三维人脸建模及应用研究[D].北京工业大学计算机学院,2005.
[70]邹北骥,彭永进,伍立华,彭群生.基于面分块的人脸造型技术研究[J].电子学报,2001,29(11):1533-1535.
[71]邹北骥,彭永进,伍立华,彭群生.基于物理模型的人脸表情动画技术研究[J].计算机学报,2002,25(3):331-336.
[72]杜平,徐大为,刘重庆.特定人的三维人脸模型生成与应用[J].上海交通大学学报,2003,37(3):435-439.
[73] BEUMIER C, ACHEROY M. Automatic3D face authentication[J]. Image andVision Computing.2000,18(1):315-321.
[74] Messer K, Matas J, Kittler J, Luettin J, maitre G. Xm2vtsdb: The extendedm2vts database[DB]. In Second International Conference of Audio andVideo-based Biometric Person Authentication, Washington, DC, USA, March1999:72-77.
[75] Moreno A B, Sanchez A, Gavab D B. A3D Face Database[DB]. Proc. of the2nd COST275Workshop on Biometrics on the Internet, Vigo (Spain),2004.
[76] Savran A, Alyüz N, Dibeklio lu H, eliktutan O, G kberk B, Sankur B, AkarunL, Bosphorus Database for3D Face Analysis[DB], The First COST2101Workshop on Biometrics and Identity Management.2008:1-11.
[77][DB/OL]. http://www-users.cs.york.ac.uk/~nep/research/3Dface/,2006.
[78] Phillips J, Flynn P, Scruggs T, Bowyer K, Chang J, Hoffman K, Marques J, MinJ, Worek W. Overview of the face recognition grand challenge[C]. Proceedingsof IEEE Conference of Computer Vision and Pattern Recognition,2005,1:947–954.
[79] BESLP J, MCKAY N D. A method for registration of3-D shapes[C]. IEEETransactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[80] RUSINKIEWICZ S, LEVOY M. Efficient variant of the ICP algorithm[C]. In:Proceedings of the Third International Conference on3-D Digital Imaging andModeling,2001:145-152.
[81] SALVI J, MATABOSCH C, FOFI D, et al. A review of recent range imageregistration methods with accuracy evaluation[J]. Image and VisionComputing,2007,25(5):578-596
[82] Rusinkiewicz S, Levoy M. Efficient Variants of the ICP Algorithm[C]. InProceedings of the International Conference on3D Digital Imaging andModeling,2001:145-152
[83] CHEN Y, MEDIONI G, Object modeling by registration of multiple rangeimages[J]. Image and Vision Computing,1992,10(3):145-155.
[84] Duchon J, Splines minimizing rotation invariant seminorms in sobolevspaces[C]. constructive theory of functions of several variables,1976:85-91
[85] Levoy M, Pulli K, Curless B, et al. The Digital Michelangelo Project:3DScanning of Large Statues[C]. Proceedings of SIGGRAPH’00, New York: ACMPress,2000:131-144
[86] Krishnamurthy V, Levoy M. Fitting smooth surfaces to dense polygonmeshes[C], Proceedings of SIGGRAPH’96, Addison Wesley,1996:313-324.
[87] Taubin G. Dual mesh resampling[C]. Ninth Pacific Conference on ComputerGraphics and Applications,2001:180-188.
[88] Holland J H. Adaptation in Natural and Artificial Systems[J]. MIT Press,1975.
[89]周明,孙树栋.遗传算法原理及应用[J].北京:国防工业出版社,2000,4:32-38
[90] David B, Fogel. An Introduction to Simulated Evolutionary Optimization[J],IEEE Transactions on Neural Networks.1994,5(1):3-14
[91] Murata, Tadahiko, Ishibuchi, Hisao, Tanaka, Hideo. Genetic algorithms for flowshop scheduling problems[J], Computers&Industrial Engineering,1996,30(4):1061-1071.
[92] Renner G, Ekárt A. Genetic algorithms in computer aided design,Computer-Aided Design[J].2003,35(8):709-726
[93] Smith, Greg C, Smith, Shana S F. An enhanced genetic algorithm for automatedassembly planning[C], Robotics and Computer-Integrated Manufacturing,2002,18(5-6):355-364
[94] Torre F, Gross R, Baker S, Kumar V. Representational oriented componentanalysis (ROCA) for face recognition with one sample image per trainingclass[C], Proceedings of IEEE Computer Society Conference on ComputerVision and Pattern Recognition,2005:266–273.
[95] Chen J, Chen X L, Gao W. Expand training set for face detection by GAresampling[C], Proceedings of Automatic Face and Gesture Recognition,2004:73-79.
[96] Umar M, Simon J, Jan K. Visualization generating novel facial images[C],Proceedings of SIGGRAPH09, ACM,2009:28-31.
[97] Efros A A, Freeman W T.. Image Quilting for Texture Synthesis and Transfer[C].Proceedings of the ACM SIGGRAPH Conference on Computer Graphics,2001:341-346.
[98] Lipman Y, Sorkine O, Cohen-Or D, Levin D, Rossi C, Seidel H P, Differentialcoordinates for interactive mesh editing[C], Proceedings of Shape ModelingInternational,2004:181-190.
[99] Yizhou Y, Kun Z, Dong X, Xiaohan S, Hujun B, Baining G, Heung-Yeung S.,Mesh editing with Poisson-based gradient field manipulation[J]. ACMTransactions on Graphics,2004,23(4):644-651.
[100] FATTAL R, LISCHINSKI D, WERMAN M. Gradient domain high dynamicrange compression[J]. ACM Trans.2001,21(3):249–256.
[101] P′EREZ P, GANGNET M, AND BLAKE, A.2003. Poisson imageediting[J]. ACM Trans. Graph.22,3,313–318.
[102] LEVIN A, ZOMET A, PELEG S, WEISS Y. Seamless image stitching in thegradient domain[C]. Europeon Conference on Computer Vision,2004:377–389.
[103] AGARWALA A, DONTCHEVA M, AGRAWALA M, DRUCKER S,COLBURN A. CURLESS B., SALESIN D., COHEN M. Interactive digitalphotomontage[J]. ACM Trans. Graph.2004,23(3):294–302.
[104] MCCANN J, POLLARD N S. Real-time gradient domain painting[J]. ACMTransactions on Graphics,2008,27,3.
[105] Hotelling H, Relations between two sets of variants[J], Biometrika,1936,28:321–377.
[106] Viola P, Wells W M. Alignment by Maximization of Mutual Information[J].International Journal of Computer Vision,1997,24(2):137-154.
[107] Fletcher R, Practical Methods of Optimization, UnconstrainedOptimization[J], John Willy and Sons, Chichester,1980.
[108] Kennedy J, Eberthart R, Particle swarm optimization[C]. Proceedings ofIEEE Conference on Neural Networks,1995,4:1942–1948.
[109] Eberhart R, Kennedy J. A new optimizer using particle swarm theory[C].Proceedings of International Conference Symposium on Micro Machine andHuman Science. Piscataway, NJ,1995:39-43.
[110] Shi Y, Eberhart R C. A modified particle swarm optimizer[C]. Proceedingsof IEEE International Conference on Evolutionary Computation,1998:69-73.
[111] Shi Y, Eberhart R C. Empirical study of particle swarm optimization[C].Proceedings of the World Multi conference on Systematic, Cybernetics andInformatics, Orlando, FL,2000:1945-1950.
[2] Pighin F, Hecker J, Lischinski D, Szeliski R, Salesin D H. Synthesizing realisticfacial expressions from photographs [C]. Proceedings of SIGGRAPH,1998:75-84.
[3] Mehrabian A. Communication without words [J]. Psychology Today,1968,2(4):53-56.
[4] Parke F I. Parameterized models for facial animation[C]. IEEE ComputerGraphics and Applications,1982,2(9):61-68
[5] Parke F I. A model for human faces that allows speech synchronizedanimation[J]. Journal of Computers and Graphics,1975,1(1):1-4.
[6] Parke F I. Parameterized models for facial animation[C]. IEEE ComputerGraphics,1982,2(9):61-68.
[7] Parke F I. Control Parameterization for facial animation[J], ComputerAnimation, Tokyo: Springer-Verlag,1991:3-13.
[8] Parke F I, Waters K. Computer Facial Animation[J], AK Peters,1994.
[9] Pighin F, Auslander J, Lischinski D, et al. Realistic facial animation using imagebased3D morphing[J]. Technical Report TR-97-01-03, University ofWashington, Computer Science Department, January1997.
[10] Pighin F. Modeling and animating realistic faces from images[D]. Ph. Ddissertation, University of Washington,1999.
[11] Lee W S, Escher M, Sannier G, Magnenat-Thalmann N. MPEG-4CompatibleFaces from Orthogonal Photos[C]. International Conference on ComputerAnimation, Geneva, Switzerland,1999:186-194.
[12] Lee W S, Kalra P, Magnenat-Thalmann N. Model Based Face Reconstructionfor Animation[C]. Proceeding of Multimedia Modeling, Singapore,1997,323-338.
[13] Lee W S, Magnenat-Thalmann N. Fast Head Modeling for Animation[J].Journal Image and Vision Computing,2000,18(4):355-364.
[14] Liu Z C, Shan Y, Zhang Z.Y. Expressive expression mapping with ratioimages[C]. Proceedings of SIGGRAPH’01,2001:71-276.
[15] Liu Z C, Zhang Z Y, Jacobs C., Cohen M. Rapid modeling of animated facesfrom video images[C]. ACM Multimedia,2000:475-476.
[16] Horace H S., Yin L J. Constructing a3D Individualized Head Model from TwoOrthogonal Views[J]. The Visual Computer,1996,12:254-266.
[17] Akimoto T, Suenaga Y, and Wallace R S. Automatic Creation of3D FacialModels[J]. IEEE Computer Graphics and Applications,1993,13(4):16–22.
[18] Horn B, Obtaining shape from shading information[C]. In P. Winston, editor,The Psychology of Computer Vision. McGraw-Hill, New York,1975.
[19] Horn B, Brooks M, Shape from Shading. The MIT Press,1989.
[20] CATTELAN M, HANCOCK E R. Acquiring height maps of faces from a singleimage[C], Proceedings of the2nd International Symposium on3D DataProcessing, Visualization and Transmission,2004:183-190
[21] CATTELAN M, HANCOCK E R. Acquiring height data from a single image ofa face using local shape indicators[J], Computer Vision and ImageUnderstanding,2006,103(1):64-79.
[22] SMITH W A P, HANCOCK E R. Recovering facial shape and albedo using astatistical model of surface normal direction[C]. IEEE International Conferenceon Computer vision.2005:588-595
[23] Zhao W, Chellappa R. Symmetric shape-from-shading using self-ratio image[J].International Journal of Computer Vision,2001:55–75.
[24] Prados E, Camilli F, and Faugeras O. A unifying and rigorous shape fromshading method adapted to realistic data and applications[J]. J. Math. ImagingVis.,2006,25(3):307–328.
[25] Prados E, Faugeras O. Shape from shading: a well-posed problem?[C]. IEEEConference on Computer Vision and Pattern Recognition.2005,2:870–877.
[26] Kemelmacher I, Basri R. Molding face shapes by example[C]. EuropeonConference on Computer Vision,2006:277–288.
[27] Dovgard R, Basri R. Statistical symmetric shape from shading for3d structurerecovery of faces[C]. Proceedings of the European Conference on ComputerVision,2004:108–116.
[28] Jollife I T. Principal Component Analysis[J]. Springer-Verlag, New York,1986.
[29] Atick J J, Griffin P A, Redlich A N. Statistical approach to shape from shading:Reconstruction of3d face surfaces from single2d images[J]. NeuralComputation,1996,8:1321–1340.
[30] Smith W A P, Hancock E R. Recovering facial shape and albedo using astatistical model of surface normal direction[C]. IEEE International Conferenceon Computer Vision,2005:588–595.
[31] Blanz V, Vetter T. A morphable model for the synthesis of3D faces[C].Proceedings of SIGGRAPH’99,1999:187–194.
[32] Ullman S, Basri R. Recognition by Linear Combinations of Models[J]. A.I.Memo1152, MIT Artificial Intelligence Laboratory, Cambridge, MA, USA,1989.
[33] Shashua A. Projective structure from two uncalibrated images: Structure frommotion and recognition[J]. A.I. Memo1363, MIT,1992.
[34] Choi C S., Okazakit T, Harashima H., Takebe T. A system of analyzing andsynthesizing facial images[C]. In Proc. IEEE International Conference onSymposium of Circuit and Syatems,1991:2665–2668.
[35] Poggio T, Brunelli R. A novel approach to graphics[J]. A.I. Memo1354, MIT,1992
[36] Poggio T., Vetter T. Recognition and Structure from one2D Model View:Observations on Prototypes[J], Object Classes and Symmetries. A.I. Memo1354, MIT,1992.
[37] Vetter T, Poggio T. Linear objects classes and image synthesis from a singleexample image[J]. A.I. Memo1531, MIT,1995.
[38] Jones M J, Poggio T. Model-based matching by linear combinations ofprototypes[J]. A.I. Memo1583, MIT,1996.
[39] Vetter T, Blanz V. Estimating coloured3d face models from single images: Anexample based approach[C]. European Conference on Computer VisionFreiburg,1998:499-513.
[40]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.
[41]晏洁,高文.基于一般人脸模型修改的特定人脸合成技术[J]，计算机辅助设计与图形学,1999,11(5):389-394.
[42] Gao W, Chen Y Q, Wang R, Shan S G, Jiang D L. Learning and SynthesizingMPEG-4Compatible3-D Face Animation from Video Sequence[J]. IEEETransactions on Circuits and Systems for Video technology.2003,13(11):1119-1128.
[43]陈益强,高文,王兆其,姜大龙.基于机器学习的语音驱动人脸动画方法[J].软件学报,2003,14(2):215-221.
[44] Shan S G., Gao W, Yan B, et al. Individual3Dface synthesis based onorthogonal photos and speech-driven facial animation[C].2000InternationalConference on Image Processing,2000,1(3):238-241.
[45]梅丽,鲍虎军.基于实拍图像的人脸真实感重建[J].计算机学报,2000,23（9）:996-1002
[46]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.
[47]张青山,陈国良.具有真实感的三维人脸动画[J].软件学报,2003,14(3):643-650.
[48]张翔宇,华蓓,陈意云.人脸建模和动画的基本技术[J].计算机辅助设计与图形学学报，2001,13(4):343-347.
[49]王奎武,王询,董兰芳,陈意云.一个MPEG一兼容的人脸动画系统[J].计算机研究与发展.2001,38(5):529-535.
[50] Chen T B, Yin B C, Huang W J, and Kong D H. Animating Human Face underArbitrary Illumination[C]. In Proceedings of Pacific Graphics'01, Tokyo, Japan,2001:314-321.
[51]尹宝才,胡永利,程世铨,谷春亮.基于形变模型的人脸建模及其应用综述[J].北京工业大学学报,2003,29(3):364-371.
[52]尹宝才,孙艳丰,王成章,盖赟. BJUT-3D三维人脸数据库及其处理技术[J].计算机研究与发展.2009,46(6):1009-1018.
[53]胡永利,尹宝才,程世锉,谷春亮,刘文韬.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.
[54] Hu Y L, Yin B C, Sun Y F, Cheng S Q.3D Face Animation Based on MorphableModel[J]. Journal of Information and Computational Science,2005,2(1):35-40.
[55] Hu Y L, Yin B C, Kong D H, A new facial feature extraction method based onlinear combination model[C], Proceedings IEEE/WIC International Conferenceon Web Intelligence,2003:520-523.
[56] Hu Y L, Yin B C, Cheng S Q, Gu C.L, A3D facial combination model based onmesh resampling[C], International Conference on Signal ProcessingProceedings,2004:1231-1234.
[57] Hu Y L, Yin B C, Sun Y F. Multi-lighting3D face morphable model based onmesh resampling[C].2005IEEE International Conference on Acoustics, Speech,and Signal Processing (IEEE Cat. No.05CH37625),2005,1121-1124.
[58] Hu Y L, Yin B C, Cheng S Q, Gu C L. An Improved Morphable Model For3DFace Synthesis[C]. The Third International Conference on Machine Learningand Cybernetics.2004:26-29.
[59] Wang C Z, Yin B C, Shi Q, Sun Y F.3D Face Correspondence Based onUniform Mesh Resampling Combined with Mesh Simplification[J], Journal ofComputational Information Systems,2005,1(2):343-350.
[60] Yin B C, Wang C Z, Shi Q, Sun Y F. MPEG-4Compatible3D Facial AnimationBased on Morphable Model[C], Proceedings of the Fourth InternationalConference on Machine Learning and Cybernetics, Guangzhou,2005:4936-4941.
[61] Wang C Z, Yin B C, Shi Q, Sun Y F. An improved3D face synthesis based onmorphable model[C],2nd International Conference on Artificial IntelligenceApplications and Innovations, ARTIFICAL INTELLIGENCE APPLICATIONSAND INNOVATIONS II:2005:183-187,ISTP）
[62] Wang C Z, Yin B C, Bai X M, Sun Y F. Improved Genetic Algorithm BasedModel Matching Method for3D Face Synthesis[C], International Symposiumon Computing and Its Application in Information Science,2005:381-384.
[63] Yin B C, Wang C Z, Shi Q, Sun Y F, Morphable Model Based FacialAnimation[C]. International Symposium on Computing and Its Application inInformation Science,2005:291-295.
[64]王成章,石勤,孙艳丰,尹宝才,三维人脸纹理改善及其在模型匹配中的应用[J],北京工业大学学报，2006,32(3):246-251.
[65]王成章,尹宝才,石勤,孙艳丰,基于形变模型的真实感三维人脸动画研究,计算机工程与应用[J],2006,42(6):33-35.
[66]王成章,尹宝才,孙艳丰,胡永利.一种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.
[67] Gu C L, Yin B C, Hu Y L, Cheng S Q. Resampling based method for pixel-wisecorrespondence between3D faces[C], International Conference on InformationTechnology: Coding and Computing,2004:614-619.
[68] Wu S N, Yin B C, Cai T. The synthesis of realistic human face[C]. ThirdInternational Conference on Advances in Multimodal Interfaces-ICMI,2000,1948:199-206.
[69]胡永利,真实感三维人脸建模及应用研究[D].北京工业大学计算机学院,2005.
[70]邹北骥,彭永进,伍立华,彭群生.基于面分块的人脸造型技术研究[J].电子学报,2001,29(11):1533-1535.
[71]邹北骥,彭永进,伍立华,彭群生.基于物理模型的人脸表情动画技术研究[J].计算机学报,2002,25(3):331-336.
[72]杜平,徐大为,刘重庆.特定人的三维人脸模型生成与应用[J].上海交通大学学报,2003,37(3):435-439.
[73] BEUMIER C, ACHEROY M. Automatic3D face authentication[J]. Image andVision Computing.2000,18(1):315-321.
[74] Messer K, Matas J, Kittler J, Luettin J, maitre G. Xm2vtsdb: The extendedm2vts database[DB]. In Second International Conference of Audio andVideo-based Biometric Person Authentication, Washington, DC, USA, March1999:72-77.
[75] Moreno A B, Sanchez A, Gavab D B. A3D Face Database[DB]. Proc. of the2nd COST275Workshop on Biometrics on the Internet, Vigo (Spain),2004.
[76] Savran A, Alyüz N, Dibeklio lu H, eliktutan O, G kberk B, Sankur B, AkarunL, Bosphorus Database for3D Face Analysis[DB], The First COST2101Workshop on Biometrics and Identity Management.2008:1-11.
[77][DB/OL]. http://www-users.cs.york.ac.uk/~nep/research/3Dface/,2006.
[78] Phillips J, Flynn P, Scruggs T, Bowyer K, Chang J, Hoffman K, Marques J, MinJ, Worek W. Overview of the face recognition grand challenge[C]. Proceedingsof IEEE Conference of Computer Vision and Pattern Recognition,2005,1:947–954.
[79] BESLP J, MCKAY N D. A method for registration of3-D shapes[C]. IEEETransactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[80] RUSINKIEWICZ S, LEVOY M. Efficient variant of the ICP algorithm[C]. In:Proceedings of the Third International Conference on3-D Digital Imaging andModeling,2001:145-152.
[81] SALVI J, MATABOSCH C, FOFI D, et al. A review of recent range imageregistration methods with accuracy evaluation[J]. Image and VisionComputing,2007,25(5):578-596
[82] Rusinkiewicz S, Levoy M. Efficient Variants of the ICP Algorithm[C]. InProceedings of the International Conference on3D Digital Imaging andModeling,2001:145-152
[83] CHEN Y, MEDIONI G, Object modeling by registration of multiple rangeimages[J]. Image and Vision Computing,1992,10(3):145-155.
[84] Duchon J, Splines minimizing rotation invariant seminorms in sobolevspaces[C]. constructive theory of functions of several variables,1976:85-91
[85] Levoy M, Pulli K, Curless B, et al. The Digital Michelangelo Project:3DScanning of Large Statues[C]. Proceedings of SIGGRAPH’00, New York: ACMPress,2000:131-144
[86] Krishnamurthy V, Levoy M. Fitting smooth surfaces to dense polygonmeshes[C], Proceedings of SIGGRAPH’96, Addison Wesley,1996:313-324.
[87] Taubin G. Dual mesh resampling[C]. Ninth Pacific Conference on ComputerGraphics and Applications,2001:180-188.
[88] Holland J H. Adaptation in Natural and Artificial Systems[J]. MIT Press,1975.
[89]周明,孙树栋.遗传算法原理及应用[J].北京:国防工业出版社,2000,4:32-38
[90] David B, Fogel. An Introduction to Simulated Evolutionary Optimization[J],IEEE Transactions on Neural Networks.1994,5(1):3-14
[91] Murata, Tadahiko, Ishibuchi, Hisao, Tanaka, Hideo. Genetic algorithms for flowshop scheduling problems[J], Computers&Industrial Engineering,1996,30(4):1061-1071.
[92] Renner G, Ekárt A. Genetic algorithms in computer aided design,Computer-Aided Design[J].2003,35(8):709-726
[93] Smith, Greg C, Smith, Shana S F. An enhanced genetic algorithm for automatedassembly planning[C], Robotics and Computer-Integrated Manufacturing,2002,18(5-6):355-364
[94] Torre F, Gross R, Baker S, Kumar V. Representational oriented componentanalysis (ROCA) for face recognition with one sample image per trainingclass[C], Proceedings of IEEE Computer Society Conference on ComputerVision and Pattern Recognition,2005:266–273.
[95] Chen J, Chen X L, Gao W. Expand training set for face detection by GAresampling[C], Proceedings of Automatic Face and Gesture Recognition,2004:73-79.
[96] Umar M, Simon J, Jan K. Visualization generating novel facial images[C],Proceedings of SIGGRAPH09, ACM,2009:28-31.
[97] Efros A A, Freeman W T.. Image Quilting for Texture Synthesis and Transfer[C].Proceedings of the ACM SIGGRAPH Conference on Computer Graphics,2001:341-346.
[98] Lipman Y, Sorkine O, Cohen-Or D, Levin D, Rossi C, Seidel H P, Differentialcoordinates for interactive mesh editing[C], Proceedings of Shape ModelingInternational,2004:181-190.
[99] Yizhou Y, Kun Z, Dong X, Xiaohan S, Hujun B, Baining G, Heung-Yeung S.,Mesh editing with Poisson-based gradient field manipulation[J]. ACMTransactions on Graphics,2004,23(4):644-651.
[100] FATTAL R, LISCHINSKI D, WERMAN M. Gradient domain high dynamicrange compression[J]. ACM Trans.2001,21(3):249–256.
[101] P′EREZ P, GANGNET M, AND BLAKE, A.2003. Poisson imageediting[J]. ACM Trans. Graph.22,3,313–318.
[102] LEVIN A, ZOMET A, PELEG S, WEISS Y. Seamless image stitching in thegradient domain[C]. Europeon Conference on Computer Vision,2004:377–389.
[103] AGARWALA A, DONTCHEVA M, AGRAWALA M, DRUCKER S,COLBURN A. CURLESS B., SALESIN D., COHEN M. Interactive digitalphotomontage[J]. ACM Trans. Graph.2004,23(3):294–302.
[104] MCCANN J, POLLARD N S. Real-time gradient domain painting[J]. ACMTransactions on Graphics,2008,27,3.
[105] Hotelling H, Relations between two sets of variants[J], Biometrika,1936,28:321–377.
[106] Viola P, Wells W M. Alignment by Maximization of Mutual Information[J].International Journal of Computer Vision,1997,24(2):137-154.
[107] Fletcher R, Practical Methods of Optimization, UnconstrainedOptimization[J], John Willy and Sons, Chichester,1980.
[108] Kennedy J, Eberthart R, Particle swarm optimization[C]. Proceedings ofIEEE Conference on Neural Networks,1995,4:1942–1948.
[109] Eberhart R, Kennedy J. A new optimizer using particle swarm theory[C].Proceedings of International Conference Symposium on Micro Machine andHuman Science. Piscataway, NJ,1995:39-43.
[110] Shi Y, Eberhart R C. A modified particle swarm optimizer[C]. Proceedingsof IEEE International Conference on Evolutionary Computation,1998:69-73.
[111] Shi Y, Eberhart R C. Empirical study of particle swarm optimization[C].Proceedings of the World Multi conference on Systematic, Cybernetics andInformatics, Orlando, FL,2000:1945-1950.