基于NURBS变形和单视角图片的人脸表情生成

doi:10.3969/j.issn.1000-3428.2017.11.037

计算机工程

基于NURBS变形和单视角图片的人脸表情生成

孙思^a,葛卫民^a,冯志勇^b,徐超^b,彭伟龙^a

(天津大学 a.计算机科学与技术学院;b.软件学院,天津 300350)

收稿日期:2016-10-17 出版日期:2017-11-15 发布日期:2017-11-15
作者简介:孙思(1989—),男,硕士研究生,主研方向为计算机图形学、模式识别;葛卫民,副教授、博士;冯志勇,教授、博士;徐超,副教授、博士;彭伟龙,博士。
基金资助:
国家自然科学基金(61304262)。

Facial Expression Generation Based on NURBS Warping and Single Perspective Images

SUN Si^a,GE Weimin^a,FENG Zhiyong^b,XU Chao^b,PENG Weilong^a

(a.School of Computer Science and Technology; b.School of Computer Software,Tianjin University,Tianjin 300350,China)

Received:2016-10-17 Online:2017-11-15 Published:2017-11-15

摘要/Abstract

摘要： 传统人脸表情重建方法大多通过线性组合的方式,难以生成精细的人脸表情,并且需要使用三维激光扫描仪得到图片,不利于推广。为此,提出一种基于非均匀有理B样条建立三维人脸表情模型的方法。根据人脸形状上与表情相关的特征点调节曲面的控制点,引入几何约束和平滑约束保证整体和局部平滑。实验结果表明,与线性方法相比,该方法鲁棒性较好,可以方便地从标准图片和无约束图片中生成较为精细的三维人脸表情。

关键词: B样条, 形式化建模, 特征点检测, 单视角, 合成图片

Abstract: In facial expression generation,most of traditional methods are difficult to produce fine facial expression by linear combination,and the images need to be obtained with 3D laser scanner,which is not conductive to the promotion of the method.In order to solve this problem,a method Non-uniform Rational B-spline(NURBS) building 3D face expression model is proposed.In this method,the control points of the surface are adjusted according to the feature points related to facial expression,and geometric constraint and smoothness constrain are to introduced to guarantee global and local smoothness.Experimental results show that compared with the linear method,this method is more robust,can easily generate fine 3D facial expression from standard image and unconstrained image.

Key words: B-spline, formal modeling, feature point detection, single perspective, synthetic image

中图分类号:

TP18

孙思,葛卫民,冯志勇,徐超,彭伟龙. 基于NURBS变形和单视角图片的人脸表情生成[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2017.11.037.

SUN Si,GE Weimin,FENG Zhiyong,XU Chao,PENG Weilong. Facial Expression Generation Based on NURBS Warping and Single Perspective Images[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.11.037.

http://www.ecice06.com/CN/Y2017/V43/I11/227

参考文献

参考文献［1］MOIZA G,TAL A,SHIMSHONI I,et al.Image-based Animation of Facial Expressions［J］.Visual Computer,2002,18(7):445-467. ［2］LUO Changwei,JIANG Chen,YU Jun,et al.Expressive Facial Animation from Videos［C］//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2014:4617-4621. ［3］KITTLER J,HILTON A,HAMOUZ M,et al.3D Assisted Face Recognition:A Survey of 3D Imaging,Modelling and Recognition Approachest［C］//Proceedings of IEEE Computer Society Conference on Computer Vision & Pattern Recognition-workshops.Washington D.C.,USA:IEEE Press,2005:114-114. ［4］BLANZ V,VETTER T.Face Recognition Based on Fitting a 3D MorphableModel［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence,2003,25(9):1063-1074. ［5］MOEINI A,MOEINI H,FAEZ K.Pose-Invariant Facial Expression Recognition Based on 3D Face Reconstruction and Synthesis from a Single 2D Image［C］//Proceedings of International Conference on Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2014:1746-1751. ［6］LI Huibin,DING Huaxiong,HUANG Di,et al.An Efficient Multimodal 2D + 3D Feature-based Approach to Automatic Facial Expression Recognition［J］.Computer Vision & Image Understanding,2015,140(C):83-92. ［7］CHI Jing,TU Changhe,ZHANG Caiming.Dynamic 3D Facial Expression Modeling Using Laplacian Smooth and Multi-scale Mesh Matching［J］.Visual Computer,2014,30(6):649-659. ［8］DAHMANE M,MEUNIER J.Prototype-based Modeling for Facial Expression Analysis［J］.IEEE Transactions on Multimedia,2014,16(6):1574-1584. ［9］HEO J,SAVVIDES M.3-D Generic Elastic Models for Fast and Texture Preserving 2-D Novel Pose Synthesis［J］.IEEE Transactions on Information Forensics & Security,2012,7(2):563-576. ［10］HOCH M,FLEISCHMANN G,GIROD B.Modeling and Animation of Facial Expressions Based on B-Splines［J］.The Visual Computer,1994,11(2):87-95. ［11］MINOI J L,JUPIT A J R,GILLIES D F,et al.Facial Expressions Reconstruction of 3D Faces Based on Real Human Data［C］//Proceedings of IEEE International Conference on Computational Intelligence and Cybernetics.Washington D.C.,USA:IEEE Press,2012:185-189. (下转第238页) (上接第233页) ［12］PIEGL L,TILLER W.The NURBS Book［M］.2nd ed.Berlin,Germany:Springer-Verlag,1997. ［13］PENG Weilong,XU Chao,FENG Zhiyong.3D Face Modeling Based on Structure Optimization and Surface Reconstruction with B-Spline［J］.Neurocomputing,2016,179(12):228-237. ［14］ASTHANA A,ZAFEIRIOU S,CHENG S,et al.Robust Discriminative Response Map Fitting with Constrained Local Models［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3444-3451. ［15］TZIMIROPOULOS G,PANTIC M.Gauss-Newton Deformable Part Models for Face Alignment In-the-Wild［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1851-1858. ［16］KEMELMACHER-SHLIZERMAN I,SEITZ S M.Face Reconstruction in the Wild［C］//Proceedings of International Conference on Computer Vision.IEEE Computer Society,2011:1746-1753. ［17］ZHU Xiangyu,LEI Zhen,YAN Junjie,et al.High-fidelity Pose and Expression Normalization for Face Recognition in the Wild［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:787-796. ［18］VAN Dam C,VELDHUIS R,SPREEUWERS L.Landmark-based model-free 3D Face Shape Reconstruction from Video Sequences［C］//Proceedings of International Conference on Biometrics Special Interest Group (BIOSIG).Washington D.C.,USA:IEEE Press,2013:1-5. 编辑刘冰

[1]	芦穗豪, 韩勇, 齐永阳, 宋国贤. 基于改进麻雀搜索算法的B样条曲线拟合方法[J]. 计算机工程, 2023, 49(1): 100-112.
[2]	吴海滨, 徐若彤, 王爱丽, 于晓洋, 岩堀祐之, 赵蓝飞, 刘赫. 基于计算机视觉的人体内腔三维重建技术综述[J]. 计算机工程, 2021, 47(10): 1-15.
[3]	夏锐, 钱振江, 刘苇. 一种基于Isabelle/HOL的安全通信协议验证方法[J]. 计算机工程, 2021, 47(1): 146-153.
[4]	欧阳恒一, 熊焰, 黄文超. 一种代币智能合约的形式化建模与验证方法[J]. 计算机工程, 2020, 46(10): 41-45,51.
[5]	耿磊,袁菲,肖志涛,张芳,吴骏,李月龙. 基于面部行为分析的驾驶员疲劳检测方法[J]. 计算机工程, 2018, 44(1): 274-279.
[6]	邢璐,唐棣. 京剧脸谱剪纸合成方法[J]. 计算机工程, 2017, 43(12): 222-226.
[7]	张启飞,郭太良. 基于多阶段决策的机器人全局路径规划算法[J]. 计算机工程, 2016, 42(10): 296-302.
[8]	张敬丽,张会清,代汝勇. 基于MIC-SURF的快速图像匹配算法[J]. 计算机工程, 2016, 42(1): 210-214.
[9]	杨龙婴,郭宇. 针对NAND闪存硬件的形式化建模[J]. 计算机工程, 2015, 41(11): 94-99.
[10]	陈青,潘日晶. 基于渐进迭代逼近的平面曲线等距线算法[J]. 计算机工程, 2015, 41(11): 287-293,298.
[11]	扈立超,史再峰,庞科,刘江明,曹清洁. 用于图像匹配的改进Harris特征点检测算法[J]. 计算机工程, 2015, 41(10): 216-220.
[12]	相艳,贺建峰,张云春,蔡莉. 基于交叉累计剩余熵的图像配准中插值方法的改进[J]. 计算机工程, 2015, 41(10): 199-203.
[13]	殷国亮,白瑞林,王永佳,李新. 一种并联机器人的时间最优轨迹规划方法[J]. 计算机工程, 2015, 41(10): 192-198.
[14]	林意, 公亚利. 边界切向量长度对B样条曲线的影响及优化[J]. 计算机工程, 2013, 39(8): 295-298.
[15]	汪友生, 张丽杰, 王志东, 陈建新. 血管内超声图像序列的边缘自动检测方法[J]. 计算机工程, 2012, 38(20): 200-203.

选择文件类型/文献管理软件名称

选择包含的内容

基于NURBS变形和单视角图片的人脸表情生成

Facial Expression Generation Based on NURBS Warping and Single Perspective Images

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于NURBS变形和单视角图片的人脸表情生成

Facial Expression Generation Based on NURBS Warping and Single Perspective Images

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价