首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于血流图和Fisher线性鉴别分析的红外人脸识别方法
引用本文:余秋冬,谢志华.基于血流图和Fisher线性鉴别分析的红外人脸识别方法[J].南昌大学学报(理科版),2010,34(2).
作者姓名:余秋冬  谢志华
作者单位:1. 天津农学院,计算机科学与信息工程系,天津,300384
2. 江西科技师范学院,光电子与通信重点实验室,江西,南昌,330013
基金项目:国家自然科学基金资助项目(60665001)
摘    要:为了从生物特征和统计角度来提高识别的性能,提出了一种基于血流图和Fisher线性鉴别(FLD)相结合的人脸识别方法,该方法首先利用血流模型把红外温谱图转换成血流图,能够利用人体的生物特征增加样本之间的类间距,并减少样本之间类内距,然后从统计特性出发,对血流图进行能最大化类间距和类内距的Fisher线性分析法。实验证明,血流图增加类间距和类内距的比值(RD),本方法得到了较好的识别结果。

关 键 词:红外人脸识别  血流图  Fisher线性判别  类间距  类内距  

Infrared Face Recognition Based on Blood Perfusion and Fisher Linear Discrimination Analysis
YU Q-dong,XIE Zhi-hua.Infrared Face Recognition Based on Blood Perfusion and Fisher Linear Discrimination Analysis[J].Journal of Nanchang University(Natural Science),2010,34(2).
Authors:YU Q-dong  XIE Zhi-hua
Institution:1.Department of Computer Science&Technology/a>;Tianjin Agriculture University Tianjin/a>;Tianjin/a>;300384/a>;China/a>;2.Key Lab of Optic-Electronic and Communication/a>;Jiangxi Sciences and Technology Normal College/a>;Nanchang 330013/a>;China
Abstract:To get the good performance of infrared face recognition from the biological feature and statistical character,a novel method for infrared face recognition based on blood perfusion and Fisher linear optimal discrimination is proposed in this paper.Firstly,thermal images are converted into blood perfusion domain by blood perfusion model to enlarge between-class distance and lessen within-class distance,which makes full use of the biological feature of the human face.Then,the FLD is chosen to maximize the rat...
Keywords:infrared face recognition  blood perfusion  Fisher linear discrimination  between-class distance  within-class distance  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号