Face Synthesis From Near-Infrared To Visual Light Spectrum Using Quotient Image And Kernel-Based Multifactor Analysis | |
Zeda Zhang; Yunhong Wang; Zhaoxiang Zhang; Guangpeng Zhang | |
2011-07-11 | |
会议日期 | 11-15 July 2011 |
会议地点 | Barcelona, Spain |
关键词 | Kernel-based Multifactor Analysis Near-infared Visual Light Synthesis Quotient Image |
英文摘要 | This paper addresses the problem of synthesizing an artificial visual light (VIS) facial image from near-infrared (NIR) input. After extensively assessing photic characteristics of tissues at human skin surface, we propose a framework for this task. Firstly, we take the quotient images for training and reconstruction, so that information related to face structure can be preserved. Secondly, to handle heterogeneous blur resulted from multiple scattering within tissues, we introduce kernel based strategy as a powerful nonlinear analyzing instrument. Finally, as in our application the image ensembles involve multiple factors, a tensor structure is employed to transform heterogeneous face data into uniform subspaces. Comparative results show that our synthesized images are both suited for human vision and discriminative for machine recognition. |
会议录 | ICME 2011 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/13284] |
专题 | 自动化研究所_类脑智能研究中心 |
通讯作者 | Zhaoxiang Zhang |
推荐引用方式 GB/T 7714 | Zeda Zhang,Yunhong Wang,Zhaoxiang Zhang,et al. Face Synthesis From Near-Infrared To Visual Light Spectrum Using Quotient Image And Kernel-Based Multifactor Analysis[C]. 见:. Barcelona, Spain. 11-15 July 2011. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论