基于MALS双线性分解的表情合成

doi:10.16182/j.issn1004731x.joss.17-0144

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (4): 671-678.doi: 10.16182/j.issn1004731x.joss.17-0144

基于MALS双线性分解的表情合成

郭加赐^1,2, 戴树岭^1,2

1. 北京航空航天大学虚拟现实技术与系统国家重点实验室,北京 100191;
2. 北京航空航天大学自动化科学与电气工程学院,北京 100191

收稿日期:2017-03-24 修回日期:2017-05-16 出版日期:2019-04-08 发布日期:2019-11-20
作者简介:郭加赐(1993-),男,山东郯城,硕士,研究方向为虚拟现实与飞行仿真;戴树岭(1966-),男,回族,河北,博士,教授,研究方向为虚拟现实与飞行仿真。

Facial Expression Synthesis Using MALS-based Bilinear Factorization Model

Guo Jiaci^1,2, Dai Shuling^1,2

1. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China;
2. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China

Received:2017-03-24 Revised:2017-05-16 Online:2019-04-08 Published:2019-11-20

摘要/Abstract

摘要： 表情合成研究是虚拟现实技术领域一项富有建设性和创造性的课题。使用双线性模型(Bilinear Model)分离出人的身份因素和表情因素来进行表情合成。在计算双线性模型的转移(Translation)问题时需要重复进行矩阵的逆运算来得到人的身份和表情信息,而当观测数据具有相关性或存在噪声信息时,该过程可能会不稳定。针对双线性模型在表情合成中的稳定性问题,通过在双线性模型转移过程引入改进迭代最小二乘法(Modified Iterative Least Square,MALS),使得该过程的计算具有更强的稳定性。设计实验进行验证,实验结果证明了方法的有效性。

关键词: 表情合成, 双线性模型, 转移, 改进迭代最小二乘

Abstract: Study on the facial expression synthesis is a constructive and creative subject in the field of virtual reality technology. The bilinear model is used for facial expression synthesis by separating the identity factor and the expression factor. The translation procedure in the bilinear model always requires a repetitive computation of matrix inverse operations to reach the identity factor and the expression factor. This computation may be instable when the observation data has the correlation or noisy information. In order to increase the stability of the bilinear model for expression synthesis, the modified iterative least square (MALS) regression is introduced into the translation procedure to stabilize the computation. Experimental results demonstrate the effectiveness of the method.

Key words: facial expression synthesis, bilinear model, translation, MALS

中图分类号:

TP391.9

郭加赐, 戴树岭. 基于MALS双线性分解的表情合成[J]. 系统仿真学报, 2019, 31(4): 671-678.

Guo Jiaci, Dai Shuling. Facial Expression Synthesis Using MALS-based Bilinear Factorization Model[J]. Journal of System Simulation, 2019, 31(4): 671-678.

参考文献

[1] S Agianpuye, J L Minoi.3D Facial Expression Synthesis: a Survey[C]// International Conference on Information Technology in Asia, USA: IEEE, 2013: 1-7.
[2] X Wan, X Jin.Data-Driven Facial Expression Synthesis via Laplacian Deformation[J]. Multimedia Tools and Applications (S1380-7501), 2012, 58(1): 109-123.
[3] Yihao Zhang,Weiyao Lin, Bing Zhou, et al.Facial Expression Cloning with Elastic and Muscle Models[J]. Journal of Visual Communication & Image Representation (S1047-3203), 2015, 25(5): 916-927.
[4] H Liang, R Liang, M Song, et al.Coupled Dictionary Learning for the Detail-Enhanced Synthesis of 3-D Facial Expressions[J]. IEEE Transactions on Cybernetics (S1083-4419), 2016, 46(4): 890-901.
[5] Chang Jianglong, Zheng Ying, Wang Zengfu.Facial Expression Analysis and Synthesis: a Bilinear Approach[C]// IEEE International Conference on Information Acquisition, USA: IEEE, 2007: 457-464.
[6] J B Tenenbaum, W T Freeman.Separating Style and Content with Bilinear Models[J]. Neural Comput (S0899-7667), 2000, 12(6): 1247-1283.
[7] MS Cheema, A Eweiwi, C Bauckhage. Human Activity Recognition by Separating Style and Content[J]. Pattern Recognition Letters (S0167-8655), 2014, 50: 130-138.
[8] HAÏFA NAKOURI, MOHAMED LIMAM. A New Bilinear Approach for Incremental Visual Learning and Recognition[J]. International Journal of Pattern Recognition & Artificial Intelligence (S0218-0014), 2013, 27(5): 487-496.
[9] X Sun,X Zhang,J Yang,et al.Voice Conversion using Bilinear Model Integrated with Joint GMM-based Classification[C]// IEEE Third International Conference on Information Science & Technology, USA: IEEE, 2013: 1225-1228.
[10] Dongsoo Shin, Hyung-Soo Lee, Daijin Kim.Illumination-Robust Face Recognition using Ridge Regressive Bilinear Models[J]. Pattern Recognition Letters (S0167-8655), 2008, 29: 49-58.
[11] Zhicai Ou, Peng Wang, Jianhua Su, et al.Sub-Pattern Bilinear Model and its Application in Pose Estimation of Work-Pieces[J]. Neurocomputing (S0925-2312), 2012, 83: 176-187.
[12] Wang Jihong, Philip K Hopke, Thomas M Hancewicz, et al.Application of Modified Alternating Least Squares Regression to Spectroscopic Image Analysis[J]. Analytica Chimica Acta (S0003-2670), 2003, 476: 93-109.
[13] S Milborrow, F Nicolls.Active Shape Models with SIFT Descriptors and MARS[C]// 2014 International Conference on Computer Vision Theory and Applications (VISAPP), Portugal: SCITEPRESS, 2014: 380-387.
[14] Lundqvist D, Flykt A, Öhman A.The Karolinska Directed Emotional Faces - KDEF, CD ROM from Department of Clinical Neuroscience[M]. Psychology section: Karolinska Institutet, 1998.
[15] Duda R, Hart P, Stork P.Pattern Classification[M]. New York: Wiley, 2001.

基于MALS双线性分解的表情合成

Facial Expression Synthesis Using MALS-based Bilinear Factorization Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	王霄汉, 张霖, 赖李媛君, 谢堃钰, 胡听春. 基于DEVS原子模型的智能体离散仿真构建方法[J]. 系统仿真学报, 2022, 34(2): 191-200.
[2]	刘义才, 刘斌, 石安伟. 区间化随机时延的网络控制系统建模与控制[J]. 系统仿真学报, 2018, 30(2): 654-663.
[3]	路阳, 衣淑娟, 任伟建, 刘建东. 具有未知转移概率Markovian神经网络渐近稳定性研究[J]. 系统仿真学报, 2017, 29(2): 235-240.
[4]	王晓慧, 马昕, 秦斌, 李贻斌. 仿生眼注视转移运动控制策略研究[J]. 系统仿真学报, 2016, 28(6): 1380-1386.