[1]江 粼,房小兆,滕少华*.基于全局-局部保持投影的稀疏降维方法[J].江西师范大学学报(自然科学版),2021,(01):46-54.[doi:10.16357/j.cnki.issn1000-5862.2021.01.07]
　JIANG Lin,FANG Xiaozhao,TENG Shaohua*.The Sparse Dimensional Reduction Based on Globality-Locality Preserving Projection[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(01):46-54.[doi:10.16357/j.cnki.issn1000-5862.2021.01.07]
点击复制

基于全局-局部保持投影的稀疏降维方法()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年01期
页码:
46-54
栏目:
出版日期:
2021-02-10

文章信息/Info

Title:
The Sparse Dimensional Reduction Based on Globality-Locality Preserving Projection
文章编号:
1000-5862(2021)01-0046-09
作者:
江 粼1; 房小兆2; 滕少华1*
1.广东工业大学计算机学院,广东广州 510006; 2. 广东工业大学自动化学院,广东广州 510006
Author(s):
JIANG Lin1; FANG Xiaozhao2; TENG Shaohua1*
1.School of Computers,Guangdong University of Technology,Guangzhou Guangdong 510006,China; 2.School of Automation,Guangdong University of Technology,Guangzhou Guangdong 510006,China
关键词:
局部结构保持投影;  线性重构;  稀疏约束;  降维
Keywords:
locality preserving projection;  linear reconstruction;  sparse constraint;  dimensionality reduction
分类号:
O 211.67
DOI:
10.16357/j.cnki.issn1000-5862.2021.01.07
文献标志码:
A
摘要:
该文提出了一种基于全局-局部结构保持的稀疏投影模型(GLSPP).通过对投影数据进行线性重构来保持数据的全局结构,从而保留投影数据的全局信息.通过约束重构系数矩阵与相似性矩阵的相似性来保持全局保持数据和局部保持投影数据的一致性.同时,对重构系数矩阵和相似性矩阵进行稀疏约束,保留主要信息,以减少冗余信息的干扰.在公开的4个人脸与物体数据集上的实验结果显示:该方法具有较高的分类准确率.
Abstract:
The global-local structure preserving sparse projection model(GLSPP)is proposed in this paper.The global structure of the projection data is preserved by linear reconstruction of the projection data,thus preserving the global information of the projection data.By constraining the similarity between reconstruction coefficient matrix and similarity matrix,the consistency of global preserving data and local preserving projection data is maintained.At the same time,sparse constraints to the reconstruction coefficient matrix and similarity matrix are applied to retain the main information in order to reduce the interference of redundant information.Experimental results on four face and object datasets show that the proposed algorithm has good classification accuracy.

参考文献/References:

[1] Jain A K,Duin R P W,Mao Jianchang.Statistical pattern recognition:a review[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):4-37.
[2] Roweis S T,Saul L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323-2326.
[3] Liu Yang,Nie Feiping,Gao Quanxue,et al.Flexible unsupervised feature extraction for image classification[J].Neural Networks,2019,115:65-71.
[4] Yao Chao,Liu Yafeng,Jiang Bo,et al.LLE score:a new filter-based unsupervised feature selection method based on nonlinear manifold embedding and its application to image recognition[J].IEEE Transactions on Image Processing,2017,26(11):5257-5269.
[5] Yao Chao,Lu Zhaoyang,Li Jing,et al.A subset method for improving Linear Discriminant Analysis[J].Neurocomputing,2014,138:310-315.
[6] Fang Xiaozhao,Han Na,Wu Jigang,et al.Approximate low-rank projection learning for feature extraction[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(11):5228-5241.
[7] Lan Xiangyuan,Ma A J,Yuen P C,et al.Joint sparse representation and robust feature-level fusion for multi-cue visual tracking[J].IEEE Transactions on Image Processing,2015,24(12):5826-5841.
[8] Belhumeur P N,Hespanha J P,Kriegman D J.Eigenfaces vs. Fisherfaces:recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[9] Abdi H,Williams L J.Principal component analysis[J].Wiley Interdisciplinary Reviews:Computational Statistics,2010,2(4):433-459.
[10] Xu Lei,Iosifidis A,Gabbouj M.Weighted linear discriminant analysis based on class saliency information[C]∥2018 25th IEEE International Conference on Image Processing,October 7-10,2018,Megaron Athens International Conference Centre,Athens:IEEE,2018:2306-2310.
[11] KanMeina,Shan Shiguang,Zhang Haihong,et al.Multi-view discriminant analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(1):188-194.
[12] Lai Zhihui,Xu Yong,Chen Qingcai,et al.Multilinear sparse principal component analysis[J].IEEE Trans Neural Netw Learn Syst,2014,25(10):1942-1950.
[13] He Xiaofei,Niyogi P.Locality preserving projections[J].Advances in Neural Information Processing Systems,2003,16(1):186-197.
[14] Cai Deng,He Xiaofei.Orthogonal locality preserving indexing[EB/OL].[2020-06-11].https://dl.acm.org/doi/10.1145/1076034.1076039.
[15] Liu Zhonghua,Yin Jun,Jin Zhong.Locality preserving projections based on L1 graph[EB/OL].[2020-06-11].http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=5659156.
[16] Wright J,Yang A Y,Ganesh A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[17] Gou Jianping,Du Lan,Cheng Keyang,et al.Discriminative sparsity preserving graph embedding[EB/OL].[2020-06-11].http://ieeexplore.ieee.org/document/7744330/.
[18] Swets D L,Weng Juyang.Hierarchical discriminant analysis for image retrieval[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):386-401.
[19] Qiao Lishan,Chen Songcan,Tan Xiaoyang.Sparsity preserving projections with applications to face recognition[J].Pattern Recognition,2010,43(1):331-341.
[20] Murray J F,Kreutz-Delgado K.Visual recognition and inference using dynamic overcomplete sparse learning[J].Neural Computation,2007,19(9):2301-2352.
[21] Amaldi E,Kann V.On the approximability of minimizing nonzero variables or unsatisfied relations in linear systems[J].Theoretical Computer Science,1998,209(1/2):237-260.
[22] Donoho D L.For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution[J].Communications on Pure and Applied Mathematics,2006,59(6):797-829.
[23] Xu Xing,Shen Fumin,Yang Yang,et al.Learning discriminative binary codes for large-scale cross-modal retrieval[J].IEEE Transactions on Image Processing,2017,26(5):2494-2507.
[24] Cai Jianfeng,Candès E J,Shen Zuowei.A singular value thresholding algorithm for matrix completion[J].SIAM Journal on Optimization,2010,20(4):1956-1982.
[25] Georghiades A S,Belhumeur P N,Kriegman D J.From few to many:illumination cone models for face recognition under variable lighting and pose[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):643-660.

备注/Memo

备注/Memo:
收稿日期:2020-02-18
基金项目:国家自然科学基金(61772141,61972102),科技部国家重点研发计划(2018YFB1802400),广东省重点领域研发计划(2020B010166006),广东省科技计划(2019B110210002,2019B010121001,2019B020208001,2019B010118001)和广州市科技计划(201903010107)资助项目.
通信作者:滕少华(1962-),男,江西南昌人,教授,博士,主要从事大数据、数据挖掘、数字音频分析与处理、网络安全方面的研究.E-mail:shteng@gdut.edu.cn
更新日期/Last Update: 2021-04-10