| 一种有监督的线性降维人脸识别算法 |
| |
| 引用本文： | 郭丽,郑忠龙,贾炯,张海新,付芳梅.一种有监督的线性降维人脸识别算法[J].计算机工程,2013(11):169-173. |
| |
| 作者姓名： | 郭丽 郑忠龙 贾炯 张海新 付芳梅 |
| |
| 作者单位： | [1]浙江师范大学数理与信息工程学院,浙江金华321004 [2]加州大学,美国默塞德95348 |
| |
| 基金项目： | 国家自然科学基金资助项目（61170109,61100119,11001247）;浙江省科技厅基金资助项目（2012C21021） |
| |
| 摘 要： | 保局投影（LPP）忽略了数据的类别标记信息且鲁棒性较差，为此，提出一种线性判别投影（LDP）算法。引入类问权重矩阵和类内权重矩阵，使各流形间的分离性最大，局部子流形的内在紧致性最小，同时通过一种鲁棒的类内处理方式使算法对outlier数据具有鲁棒性。在ORL、AR和ExtendedYaleB人脸数据集上进行实验，结果表明，与PCA、LDA、LPP、LSDA和LPDP算法相比，该算法的最佳平均识别率较高，分别可达95．3％、93．64％和96．28％，证明了算法的有效性和可靠性。
|
| 关 键 词： | 降维 流形学习 判别投影 有监督学习 保局投影 线性判别分析 |
A Supervised Linear Dimensionality Reduction Algorithm for Face Recognition |
| |
| GUO Li,ZHENG Zhong-longt＇,JIA Jiong,ZHANG Hai-xin,FU Fang-mei.A Supervised Linear Dimensionality Reduction Algorithm for Face Recognition[J].Computer Engineering,2013(11):169-173. |
| |
| Authors: | GUO Li ZHENG Zhong-longt＇ JIA Jiong ZHANG Hai-xin FU Fang-mei |
| |
| Affiliation: | 1 (1. College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua 321004, China; 2. University of California, Merced 95348, USA) |
| |
| Abstract: | Because Locality Preserving Projection（LPP） ignores the label information of the data and it is lack of robustness, this paper proposes a Linear Discriminant Projection（LDP） algorithm. By introducing between-class weight matrix and within-class weight matrix, LDP maximizes the separability of different submanifolds and minimizes the compactness of local submanifolds. Moreover, LDP is robust to outlier data by a robust within-class processing way. Compared with PCA, LDA, LPP, LSDA, LPDP, the experimental results on ORL, AR and Extended Yale B face databases show that the best average recognition rates of LDP are higher, which can reach 95.3%, 93.64% and 96.28%, and this verifies the efficiency of the proposed algorithm. |
| |
| Keywords: | dfmensionality reduction manifold learning discriminant projection supervised learning Locality Preserving Projection（LPP） Linear Discriminant Analysis（LDA） |
| 本文献已被 维普 等数据库收录！ |
|
