分块PCA加权与FLD结合的血流图红外人脸识别方法  

Weighted Block-PCA and FLD Infrared Face Recognition Method Based on Blood Perfusion Image

作　　者：谢志华[1,2] 伍世虔[1] 方志军[1] 杨寿渊[1] 卢宇[1] 

机构地区：[1]江西财经大学信息管理学院,江西南昌330013 [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

出　　处：《小型微型计算机系统》2009年第10期2069-2072,共4页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60665001;10701040)资助;江西省教育厅科技项目(GJJD9296)资助

摘　　要：传统红外人脸识别方法都是基于全局特征的识别方法,为了充分利用人脸的局部特征,提出一种基于血流图的分块PCA+FLD的红外人脸识别方法.通过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.基于各个分块的类间距与类内距比值大小(RD),分块PCA加权可以自适应地提取更适合识别的人脸局部特征,同时还可以缓解Fisher线性判别的小样本问题(零空间问题).实验表明,分块PCA+FLD并不会减少整体特征提取中有用识别信息的提取,而且可以突出局部特征对识别贡献,提高本方法的识别率.To make full use of the local character and biological feature in human faces, a novel method for infrared face recognition combining block-PCA and FLD 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. Based on the ratio of between-class distance to within-class distance （RD） in sub-blocks, block-PCA is utilized to get the local discrimination information adaptively, which can solve the small sample size problem （ the null space problem）. Finally, The Fisher linear discrimination （FLD） is applied to the holistic features combined by the extracted coefficients from the information of all sub-blocks. The experiments illustrate that the block-PCA ＋ FLD doesn＇t discard the useful discdminant information in the holistic characters and the method proposed in this paper has better performance compared with traditional methods.

关 键 词：红外人脸识别 血流图 Fisher线性判别(FLD) 分块PCA 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]