基于局部保持投影的统计不相关复合信息投影  

Uncorrelated Multiple Information Projection Based on Locality Preserving Projections

作　　者：林克正[1] 陈冬梅[1] 吴清英[2] 

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,黑龙江哈尔滨150080 [2]伊春职业学院机电工程系,黑龙江伊春153000

出　　处：《哈尔滨理工大学学报》2010年第5期75-79,共5页Journal of Harbin University of Science and Technology

基　　金：黑龙江省博士后基金(LRB00063);黑龙江省教育厅科技项目(11551087)

摘　　要：为解决在人脸识别领域的特征提取问题,提出了一种基于局部保持投影(Locality Pre-serving Projections,LPP)的统计不相关复合信息投影(UMIP).该方法是基于线性投影的子空间方法,将原始人脸图像看作是一个矩阵,通过相应的代数方法,抽取得到保持原始样本分布信息的低维子空间信息.在UMIST和Yale标准人脸图像库上的实验结果表明,UMIP算法提高了识别率.With the purpose of solving feature extraction problem in face recognition area,a new manifold learning algorithm is proposed,called Uncorrelated Multiple Information Projection（UMIP） based on Locality Preserving Projections.It is an subspace method based on linear projective maps,regards the original picture of face as a matrix,and extracts the lower dimension subspace＇s information which optimally preserves the local structure and the global information of the data set by corresponding algebraic method.The results of the experiments on UMIST and Yale face database indicate that UMIP improves recognition rate.

关 键 词：人脸识别 特征提取 局部保持投影 子空间 统计不相关 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]