ENVIRONMENT COUPLED METRICS LEARNING FOR UNCONSTRAINED FACE VERIFICATION

CASIA OpenIR > 复杂系统管理与控制国家重点实验室 > 影像分析与机器视觉

	ENVIRONMENT COUPLED METRICS LEARNING FOR UNCONSTRAINED FACE VERIFICATION
	Cai, Xinyuan; Wang, Chunheng; Xiao, Baihua; Zhou, Ji; Chen, Xue; Wang Chunheng
	2012
会议名称	2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012)
会议录名称	International Conference on Image Processing (ICIP)
页码	577-580
会议日期	2012
会议地点	Orland, Florida, U.S.A
摘要	Making recognition more reliable under unconstrained environment is one of the most important challenges for realworld face recognition. In this paper, we propose a novel approach for unconstrained face verification. First, we use a spectral-clustering method based on Structural Similarity index to estimate the captured environments of facial images. Then for each pair of environments, we learn two coupled metrics, such that facial images captured in different environments can be transformed into a media subspace, and high recognition performance can be achieved. The coupled transformations are jointly determined by solving an optimization problem in the multi-task learning framework. Experimental results on the benchmark dataset (LFW) show the effectiveness of the proposed method in face verification across varying environments.
关键词	Face Verification Metric Learning Unconstrained
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/5139
专题	复杂系统管理与控制国家重点实验室_影像分析与机器视觉
通讯作者	Wang Chunheng
推荐引用方式 GB/T 7714	Cai, Xinyuan,Wang, Chunheng,Xiao, Baihua,et al. ENVIRONMENT COUPLED METRICS LEARNING FOR UNCONSTRAINED FACE VERIFICATION[C],2012:577-580.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
201018014628026_005.（732KB）	会议论文		开放获取	CC BY-NC-SA	浏览