全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

三维人脸纹理改善及其在模型匹配中的应用

Keywords: 纹理映射,人脸库,曲线拟合,线性回归,人脸建模

Full-Text   Cite this paper   Add to My Lib

Abstract:

为改善三维人脸库的颜色纹理,基于纹理映射技术,提出了一种改善方法.使用统计学中曲线拟合与线性回归的方法,根据扫描仪获取的三维人脸库颜色纹理空间,拟合、逼近真实纹理空间,进而得到改善的颜色纹理空间,建立了三维人脸库颜色纹理空间到改善的纹理空间之间的映射关系.根据该映射关系改善了三维人脸库颜色纹理,缩小了其与真实纹理之间的差异.实验结果证明,用该方法改善后的纹理与真实纹理的差明显小于扫描得到的纹理与真实纹理之间的差;在模型匹配过程中使用改善后的纹理,可提高模型匹配速度,缩短匹配时间.

References

[1]  BLANZ V, VETTER T. Face recognition based on fitting a 3D morphable model [J]. Pattern Analysis and Machine Intelligence, 2003, 25(9): 1063-1074.
[2]  HUANG J, HEISELE B, BLANZ V. Component-based face recognition with 3D morphable models [DB/OL]. [2004-06-07]. http://cbcl.mit.edu/projects/cbcl/publications/theses/thesis-huang.
[3]  ZHANG L, SAMARAS D. Face recognition under variable lighting using harmonic image exemplars [DB/OL]. [2004-02-17]. http: // www. cs. sunysb. edu/ - samaras/papers/cvpr03-face. pdf.
[4]  BLANZ V, VETTER T. A morphable model for the synthesis of 3D faces [DB/OL]. [2004-07-03]. http: //portal, acm. org/citation, cfm? id= 311556.
[5]  Cyberware Laboratory Inc. Cyberware designs, manufactures, and sells standard and custom 3D scanning systems and software [EB/OL]. [2004-06-10]. http://www.cyberware.com.
[6]  PIGHINF, HECKER J, LISCHINSKI D, et al. Synthesizing realistic facial expressions from photographs [DB/OL]. [2003-10-19] . http: //grail, cs. Washington. edu/pub/papers/Pighin98. pdf.
[7]  刘媛媛.真实感三维人脸编辑方法的研究与实现[D].北京:北京工业大学计算机学院,2003. LIU Yuan-yuan. Research and implementation on editing method of realistic 3D face [D] . Beijing: College of Computer Science, Beijing University of Technology, 2003. (in Chinese)
[8]  KEREN D. Topologically faithful fitting of simple closed curves [J]. Pattern Analysis and Machine Intelligence, 2004, 26 (1): 118-123.
[9]  GRANICHIN O. Linear regression and filtering under nonstandard assumptions (arbitrary noise) [J]. Automatic Control, 2004, 49(10): 1830-1837.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133