Facial expressional image synthesis controlled by emotional parameters

Facial expressional image synthesis controlled by emotional parameters
复制标题

情绪参数控制的面部表情图像合成

DOI:
10.1016/j.patrec.2005.06.007
复制
发表时间:
2005-12
期刊:
Pattern Recognit. Lett.
影响因子:
--
通讯作者:
--
中科院分区:
其他
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

人脸表情图像合成是人机交互中的一项重要技术,但同时也是一项困难的任务,尤其是如何通过灵活的控制机制生成各种逼真的表情人脸图像。提出了一种参数驱动的合成真实感综合表情图像的新方法。该方法采用基于核的双因子分解模型,从一个小的训练数据库中分解身份和表情两个影响因素及其相互作用。因此,训练数据库中的面部表情图像可以被相应的身份和表情向量及其交互矩阵所覆盖。综合表情图像可以通过这些基本表情向量的线性组合以灵活的方式进行操作。为了使训练后的模型能够生成训练集之外的任何人的真实表情图像,将表情比率图像(ERI)和相对形状描述加入到我们的模型中,以增强我们的方法的表达能力。实验结果表明,该方法可以从一张与训练数据库中的人脸图像完全不同的人脸图像中成功地合成出具有真实感的人脸表情图像,并通过一个参数向量进行有效控制。
Facial expressional image synthesis is an important technique in human–computer interaction, but it is also a difficult task, especially to make various realistic expressive face images with a flexible control mechanism. In this paper, a novel parameter driven method of synthesizing realistic comprehensive expressional image is proposed. In this method a kernel-based bi-factor factorization model is adopted to decompose two influence factors, identity and expression, and their interaction from a small training database. Therefore the facial expressional images in the training database can be covered by corresponding identity and expression vectors and their interaction matrix. Comprehensive expression image can be manipulated by means of linear combination of these basis expression vectors in a flexible manner. In order to make this trained model be capable of producing realistic expressional images of any person outside the training set, expression ratio image (ERI) and relative shape description are joined into our model to enhance the expressive power of our method. Experimental results show that realistic facial expressional image can be synthesized successfully from only one picture of someone who is quite different from persons in the training database, and controlled by a parameter vector efficiently and effectively.
DOI: 10.1145/3596711.3596767
发表时间: 1992-07
期刊: Seminal Graphics Papers: Pushing the Boundaries, Volume 2
影响因子: --
作者:
Thaddeus Beier;Shawn Neely
通讯作者: Thaddeus Beier;Shawn Neely
DOI: 10.1145/1185657.1185859
发表时间: 1998-07
期刊: ACM SIGGRAPH 2006 Courses
影响因子: --
作者:
Frédéric H. Pighin;Jamie Hecker;Dani Lischinski;R. Szeliski;D. Salesin
通讯作者: Frédéric H. Pighin;Jamie Hecker;Dani Lischinski;R. Szeliski;D. Salesin
DOI: 10.1109/ca.1999.781211
发表时间: 1999-05
期刊: Proceedings Computer Animation 1999
影响因子: --
作者:
Won-Sook Lee;M. Escher;Gaël Sannier;N. Magnenat-Thalmann
通讯作者: Won-Sook Lee;M. Escher;Gaël Sannier;N. Magnenat-Thalmann
DOI: 10.1145/383259.383289
发表时间: 2001-08
期刊: Proceedings of the 28th annual conference on Computer graphics and interactive techniques
影响因子: --
作者:
Zicheng Liu;Ying Shan;Zhengyou Zhang
通讯作者: Zicheng Liu;Ying Shan;Zhengyou Zhang
DOI: 10.1145/3596711.3596787
发表时间: 1997-08
期刊: Seminal Graphics Papers: Pushing the Boundaries, Volume 2
影响因子: --
作者:
C. Bregler;M. Covell;M. Slaney
通讯作者: C. Bregler;M. Covell;M. Slaney