• 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:

Liu, Dang-Hui (Liu, Dang-Hui.) | Shen, Lan-Sun (Shen, Lan-Sun.) | Lam, Kin-Man (Lam, Kin-Man.) | Kong, Xiao (Kong, Xiao.)

收录:

EI Scopus

摘要:

Variations in lighting conditions make face recognition an even more challenging and difficult task. In this paper, a novel approach is proposed to handle the illumination problem. Our method can restore a face image captured under arbitrary lighting conditions to one with frontal illumination by using a ratio-image and an iterative algorithm. The restored images with frontal illumination are used for face recognition by means of PCA. Experimental results demonstrate that our method can achieve a higher recognition rate based on the Yale B and Yale database. Moreover, our algorithm has several advantages over other previous algorithms: (1) does not need to estimate the face surface normals and the light source directions, (2) it does not need many images captured under different lighting conditions for each person, nor a set of bootstrap images that includes many images with different illuminations, and (3) it does not need to detect accurate positions of some facial feature points and to warp image for alignment, etc.

关键词:

Algorithms Computer graphics Face recognition Image processing Image reconstruction Iterative methods Lighting Mathematical models

作者机构:

  • [ 1 ] [Liu, Dang-Hui]Sign. and Info. Proc. Laboratory, Beijing University of Technology, Beijing, 100022, China
  • [ 2 ] [Liu, Dang-Hui]No. 77, Mail Box 3380, Academy of Equipment, Command and Technology, Huairou District, Beijing, 101416, China
  • [ 3 ] [Shen, Lan-Sun]Sign. and Info. Proc. Laboratory, Beijing University of Technology, Beijing, 100022, China
  • [ 4 ] [Lam, Kin-Man]Ctr. for Multimedia Sign. Processing, Department of Electronic Engineering, Hong Kong Polytechnic University, Hong Kong, Hong Kong
  • [ 5 ] [Kong, Xiao]Sign. and Info. Proc. Laboratory, 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: 105-108

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: 1

归属院系:

在线人数/总访问数:693/3567539
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