| 一种基于局部和判别特性的降维算法 |
| |
| 引用本文： | 张国印,楼宋江,王庆军,程慧杰.一种基于局部和判别特性的降维算法[J].计算机应用研究,2009,26(9):3324-3325. |
| |
| 作者姓名： | 张国印 楼宋江 王庆军 程慧杰 |
| |
| 作者单位： | 哈尔滨工程大学,计算机科学与技术学院,哈尔滨,150001 |
| |
| 摘 要： | 提出了一种基于LPP和LDA的降维算法。该算法不仅考虑了LPP能保持局部邻近关系属性，还考虑了LDA能使降维后的数据更易于分类属性，并且该算法是线性的，很容易将新样本映射到目标空间。在人脸识别中的实验验证了算法的正确性和有效性。
|
| 关 键 词： | 维数约简 局部保持投影 线性判别分析 人脸识别 |
Dimension reduction algorithm based on locality and discriminant characteristics |
| |
| ZHANG Guo-yin,LOU Song-jiang,WANG Qing-jun,CHEN Hui-jie.Dimension reduction algorithm based on locality and discriminant characteristics[J].Application Research of Computers,2009,26(9):3324-3325. |
| |
| Authors: | ZHANG Guo-yin LOU Song-jiang WANG Qing-jun CHEN Hui-jie |
| |
| Affiliation: | (College of Computer Science & Technology, Harbin Engineering University, Harbin 150001, China) |
| |
| Abstract: | This paper proposed a dimension reduction algorithm based on LPP and LDA, which not only utilized that LPP could preserve locality, but also took into account that the LDA made the data more discriminant and thus made classification mare easier. The proposed algorithm was linear, which could map the out of sample data to the target space easily. Experiments in face recognition validate the correctness and effectiveness of the algorithm. |
| |
| Keywords: | dimension reduction locality preserving projection(LPP) linear discriminant analysis(LDA) face recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
|
