|本期目录/Table of Contents|

[1]丁铭,贾维敏,姚敏立.基于L2范数的局部保持投影算法[J].西安交通大学学报,2016,50(02):33-37.[doi:10.7652/xjtuxb201602006]
 DING Ming,JIA Weimin,YAO Minli.A Projection Algorithm with Local Preservation Based on L2 Norm[J].Journal of Xi'an Jiaotong University,2016,50(02):33-37.[doi:10.7652/xjtuxb201602006]
点击复制

基于L2范数的局部保持投影算法(PDF)

《西安交通大学学报》[ISSN:0253-987X/CN:61-1069/T]

卷:
50
期数:
2016年第02期
页码:
33-37
栏目:
出版日期:
2016-02-10

文章信息/Info

Title:
A Projection Algorithm with Local Preservation Based on L2 Norm
作者:
丁铭1贾维敏1姚敏立2
1.第二炮兵工程大学907教研室, 710025, 西安;2.第二炮兵工程大学403教研室, 710025, 西安
Author(s):
DING Ming1JIA Weimin1YAO Minli2
1. Staff Room 907, The Second Artillery Engineering University, Xi’an 710025, China;
2. Staff Room 403, The Second Artillery Engineering University, Xi’an 710025, China
关键词:
降维局部保持投影L2范数
Keywords:
dimensionality reduction locality preserving projections L2 norm
分类号:
TP391.4
DOI:
10.7652/xjtuxb201602006
摘要:
针对传统局部保持投影算法对外点敏感的问题,提出了一种基于L2范数的局部保持投影算法。该算法通过采用L2范数定义目标函数并重新定义了权值矩阵,多次迭代计算投影矩阵得到局部最小值,直至达到收敛条件,进而获得最终的最优投影矩阵;通过利用最优投影矩阵将原始数据投影到最优的投影子空间,降低高维数据维度,同时能够保持原有数据特征。合成数据实验结果表明,与传统局部保持投影算法相比,所提基于L2范数的局部保持投影算法能够有效地降低数据维度,改善了算法对外点的敏感问题,提高了算法的鲁棒性。人脸识别实验结果表明,该算法能够取得较高且较为稳定的人脸识别率,人脸识别率可达80%。
Abstract:
A projection algorithm with locality preserving projections based on the L2 norm (LPPL2) is proposed to solve the problem that objective functions of traditional projection algorithms with local preservation (LPP) are based on the squared L2 norm and very sensitive to outliers. The weight matrix of the algorithm is recalculated using an iterative method and the objective function is also simplified, as a result, the optimized projection matrix is obtained. The algorithm converges to a local optimum in each iteration. The optimized projection matrix is used to project the original data into an optimal projection subspace with reduced dimension, while the characters of original data are preserved. Experimental results on synthesized data and a comparison with the LPP algorithm show that the LPPL2 algorithm effectively reduces the data dimension and makes the algorithm more robust to outliers, it gains higher accurate and steady classification rate in face recognition, and a recognition rate of 80% is obtained.

参考文献/References:

[1]张丽梅. 面向降维的图学习研究及应用 [D]. 南京: 南京航空航天大学, 2012.
[2]YAN Shuicheng, XU Dong, ZHANG Benyu, et al. Graph embedding and extensions: a general framework for dimensionality reduction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 4051.
[3]JOLLIFFE I T. Principal component analysis [M]. Berlin, Germany: Springer, 2002: 25.
[4]MARTINEZ A M, KAK A C. PCA versus LDA [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 228233.
[5]NIYOGI P, HE Xiaofei. Locality preserving projections [J]. Advances in Neural Information Processing Systems, 2003: 153162.
[6]HE Xiaofei, YAN Shuicheng, HU Yuxiao, et al. Face recognition using Laplacian faces [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328340.
[7]何晓飞. 人脸识别的几何观点: 拉普拉斯脸 [J]. 科学观察, 2010, 5(6): 6768.
HE Xiaofei. Face recognition: Laplasse’s face [J]. Science Focus, 2010, 5(6): 6768.
[8]PTUCHA R, TSAGKATAKIS G, SAVAKIS A. Manifold learning for simultaneous pose and facial expression recognition [C]∥Proceedings of the IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2011: 30213024.
[9]TURK M, PENTLAND A. Eigenfaces for recognition [J]. Journal of Cognitive Neuroscience, 1991, 3(1): 7186.
[10]RAO A, NOUSHATH S. Subspace methods for face recognition [J]. Computer Science Review, 2010, 4(1): 117. 
[11]NIE Feiping, WANG Hua, HUANG Heng, et al. Unsupervised and semisupervised learning via L1norm graph [C]∥Proceedings of the 2011 IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2011: 22682273,
[12]HUANG Heng, XU Dong, NIE Feiping. Semisupervised dimension reduction using trace ratio criterion [J]. IEEE Transactions on Neural Network Learning System, 2012, 23(3): 519526.
[13]SYMEON N, ANASTASIOS T, LOANNIS P. Maximum margin projection subspace learning for visual data analysis [J]. IEEE Transactions on Image Processing, 2014, 23(10): 44134425.

备注/Memo

备注/Memo:
国家自然科学基金青年科学基金资助项目(61401471)
更新日期/Last Update: