【作者】 李勇智； 杨静宇； 毛洪贲；

【Author】 Li Yongzhi 1,2,Yang Jingyu 2,Mao Hongben 1 1.School of Information Science & Technology,Nanjing Forestry University,Nanjing 210037,P.R.China 2.Department of Computer Science,Nanjing University of Science & Technology,Nanjing 210094,P.R.China

【机构】 南京林业大学信息科学技术学院； 南京理工大学计算机系；

【摘要】 本文提出一种新的无监督的鉴别投影方法。这种新的方法是基于样本的局部和非局部统计量而建立的线性映射,它的鉴别准则是通过特征矢量的非局部散度与局部散度的差来刻画的,其目的是寻求一组投影轴使得投影后的样本特征矢量的非局部散度最大化,同时也使得局部散度最小化。通过在ORL人脸库和AR人脸库上进行实验,结果表明本文提出的新方法在识别率方面整体上好于局部保持投影(Lcality Preserving Projection,LPP)和无监督鉴别投影(Unsupervised Discriminant Projection,UDP),甚至超过常用的Fisher线性鉴别分析。更多还原

【Abstract】 A new unsupervised discriminant projection for dimensionality reduction of high dimensional data is presented in this paper.The new method is a linear projection based on both the local and nonlocal statistically quantities.The discriminant criterion function be characterized by difference between the nonlocal scatter and the local scatter of feature vector,seeking to find a group of projection axis that simultaneously maximizes the nonlocal scatter and minimizes the local scatter of feature vector.The experimental results on Olivetti Research Laboratory(ORL) face database and AR face database show that the proposed method consistently outperforms locality preserving projection(LPP) and unsupervised discriminant projection(UDP) ,and even outperforms Fisher linear discriminant analysis.更多还原