摘要
近10多年来,人脸识别技术在各种应用的推动下发展很快。而近几年中,为避免各种实际应用环境的限制,非约束环境下的人脸识别也得到了很大的发展。本文概述了人脸识别的一些主要方法,讨论了影响人脸识别的几个主要因素及其处理方法以及基于视频的人脸识别技术,最后指出了鲁棒的人脸识别技术的研究方向和发展前景。
Face recognition has received extensive attention because of the potential applications in many fields, such as biometrics, surveillance, access control and human-computer interface. Over the last decade, numerous algorithms have been proposed for automatic face recognition. However, face recognition under unconstrained condition is paid more attention in recent several years due to requirements of many practical applications. This paper presents a critical survey of existing literature on face recognition and some future researches are proposed.
出处
《电路与系统学报》
CSCD
2004年第1期85-94,共10页
Journal of Circuits and Systems
基金
国家自然科学基金资助项目(90104013)
863计划基金资助项目(2001AA121061
2002AA123041)
关键词
非约束环境
人脸识别
人脸特征
形变模型
视频序列
unconstrained condition
face recognition
racial features
morphable model
video sequence
