Direct orthogonal neighborhood preserving discriminant analysis

Yu Rong Lin; Qiang Wang

doi:10.4028/www.scientific.net/AMR.179-180.1254

Direct orthogonal neighborhood preserving discriminant analysis

Yu Rong Lin^*
, Qiang Wang

^*Corresponding author for this work

School of Astronautics, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Several orthogonal feature extraction algorithms based on local preserving projection have recently been proposed. However, these methods don't address the singularity problem in the high dimensional feature space, which means that the eigen-equation of orthogonal feature extraction algorithms cannot be solved directly. In this paper, we present a new method called Direct Orthogonal Neighborhood Preserving Discriminant Analysis (DONPDA), which is able to extract all the orthogonal discriminant vectors simultaneously in the high-dimensional feature space and does not suffer the singularity problem. Experimental results on ORL database indicate that the proposed DONPDA method achieves higher recognition rate than the ONPDA method and other some existing orthogonal feature extraction algorithms.

Original language	English
Title of host publication	Materials Science and Engineering
Pages	1254-1259
Number of pages	6
DOIs	https://doi.org/10.4028/www.scientific.net/AMR.179-180.1254
State	Published - 2011
Externally published	Yes
Event	2010 International Conference on Materials Science and Engineering Science, ICMSES 2010 - Shenzhen, China Duration: 11 Dec 2010 → 12 Dec 2010

Publication series

Name	Advanced Materials Research
Volume	179-180
ISSN (Print)	1022-6680

Conference

Conference	2010 International Conference on Materials Science and Engineering Science, ICMSES 2010
Country/Territory	China
City	Shenzhen
Period	11/12/10 → 12/12/10

Keywords

L DONPDA
Orthogonal feature extraction algorithms
The orthogonal discriminant vectors
The singularity problem

Access to Document

10.4028/www.scientific.net/AMR.179-180.1254

Cite this

@inproceedings{e7e86554ffb64df8b045f6000597ec9f,

title = "Direct orthogonal neighborhood preserving discriminant analysis",

abstract = "Several orthogonal feature extraction algorithms based on local preserving projection have recently been proposed. However, these methods don't address the singularity problem in the high dimensional feature space, which means that the eigen-equation of orthogonal feature extraction algorithms cannot be solved directly. In this paper, we present a new method called Direct Orthogonal Neighborhood Preserving Discriminant Analysis (DONPDA), which is able to extract all the orthogonal discriminant vectors simultaneously in the high-dimensional feature space and does not suffer the singularity problem. Experimental results on ORL database indicate that the proposed DONPDA method achieves higher recognition rate than the ONPDA method and other some existing orthogonal feature extraction algorithms.",

keywords = "L DONPDA, Orthogonal feature extraction algorithms, The orthogonal discriminant vectors, The singularity problem",

author = "Lin, \{Yu Rong\} and Qiang Wang",

year = "2011",

doi = "10.4028/www.scientific.net/AMR.179-180.1254",

language = "英语",

isbn = "9783037850169",

series = "Advanced Materials Research",

pages = "1254--1259",

booktitle = "Materials Science and Engineering",

note = "2010 International Conference on Materials Science and Engineering Science, ICMSES 2010 ; Conference date: 11-12-2010 Through 12-12-2010",

}

TY - GEN

T1 - Direct orthogonal neighborhood preserving discriminant analysis

AU - Lin, Yu Rong

AU - Wang, Qiang

PY - 2011

Y1 - 2011

N2 - Several orthogonal feature extraction algorithms based on local preserving projection have recently been proposed. However, these methods don't address the singularity problem in the high dimensional feature space, which means that the eigen-equation of orthogonal feature extraction algorithms cannot be solved directly. In this paper, we present a new method called Direct Orthogonal Neighborhood Preserving Discriminant Analysis (DONPDA), which is able to extract all the orthogonal discriminant vectors simultaneously in the high-dimensional feature space and does not suffer the singularity problem. Experimental results on ORL database indicate that the proposed DONPDA method achieves higher recognition rate than the ONPDA method and other some existing orthogonal feature extraction algorithms.

AB - Several orthogonal feature extraction algorithms based on local preserving projection have recently been proposed. However, these methods don't address the singularity problem in the high dimensional feature space, which means that the eigen-equation of orthogonal feature extraction algorithms cannot be solved directly. In this paper, we present a new method called Direct Orthogonal Neighborhood Preserving Discriminant Analysis (DONPDA), which is able to extract all the orthogonal discriminant vectors simultaneously in the high-dimensional feature space and does not suffer the singularity problem. Experimental results on ORL database indicate that the proposed DONPDA method achieves higher recognition rate than the ONPDA method and other some existing orthogonal feature extraction algorithms.

KW - L DONPDA

KW - Orthogonal feature extraction algorithms

KW - The orthogonal discriminant vectors

KW - The singularity problem

UR - https://www.scopus.com/pages/publications/79751498516

U2 - 10.4028/www.scientific.net/AMR.179-180.1254

DO - 10.4028/www.scientific.net/AMR.179-180.1254

M3 - 会议稿件

AN - SCOPUS:79751498516

SN - 9783037850169

T3 - Advanced Materials Research

SP - 1254

EP - 1259

BT - Materials Science and Engineering

T2 - 2010 International Conference on Materials Science and Engineering Science, ICMSES 2010

Y2 - 11 December 2010 through 12 December 2010

ER -

Direct orthogonal neighborhood preserving discriminant analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this