• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Yongli, Hu (Yongli, Hu.) (学者:胡永利) | Baocai, Yin (Baocai, Yin.) (学者:尹宝才) | Shiquan, Cheng (Shiquan, Cheng.) | Chunliang, Gu (Chunliang, Gu.)

收录:

EI Scopus

摘要:

In this paper, we describe a combination model for 3D facial synthesis. To construct the model it is fundamental to compute the dense point-to-point alignments among the prototypic faces acquired by Cyberware scanner. The proposed mesh resampling method overcome the alignments by the same resampling criterion to all proto-types. From the aligning prototypes the linear combination facial model is constructed. Matching the model to given facial image, the 3D face will be built automatically. To accelerate the model matching and expand the model fitting complex illumination,the multi-resolution model and multi-light model are designed. Although sharing the basic idea with the Morphable Model, the combination model has innovations in alignment strategy and illumination model. The experimental results show that the combination model have good performance in 3D face modelling.

关键词:

Algorithms Error analysis Face recognition Illuminating engineering Problem solving Three dimensional Vectors Video signal processing

作者机构:

  • [ 1 ] [Yongli, Hu]Multimedia/Intelligent Software T.L., Beijing University of Technology, Beijing 100022, China
  • [ 2 ] [Baocai, Yin]Multimedia/Intelligent Software T.L., Beijing University of Technology, Beijing 100022, China
  • [ 3 ] [Shiquan, Cheng]Multimedia/Intelligent Software T.L., Beijing University of Technology, Beijing 100022, China
  • [ 4 ] [Chunliang, Gu]Multimedia/Intelligent Software T.L., Beijing University of Technology, Beijing 100022, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2004

页码: 1233-1236

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 3

在线人数/总访问数:870/3580575
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司