Iterative subspace analysis based on feature line distance

Yanwei Pang, Yuan Yuan, Xuelong Li

Research output: Contribution to journalArticle

Abstract

Nearest feature line-based subspace analysis is first proposed in this paper. Compared with conventional methods, the newly proposed one brings better generalization performance and incremental analysis. The projection point and feature line distance are expressed as a function of a subspace, which is obtained by minimizing the mean square feature line distance. Moreover, by adopting stochastic approximation rule to minimize the objective function in a gradient manner, the new method can be performed in an incremental mode, which makes it working well upon future data. Experimental results on the FERET face database and the UCI satellite image database demonstrate the effectiveness.
Original languageEnglish
Pages (from-to)903-907
Number of pages5
JournalIEEE Transactions on Image Processing
Volume18
Issue number4
DOIs
Publication statusPublished - Apr 2009

Fingerprint

Satellites

Keywords

  • generalization performance
  • incremental analysis
  • iterative subspace analysis
  • mean square feature line distance
  • nearest feature line
  • objective function
  • projection point
  • stochastic approximation rule

Cite this

Pang, Yanwei ; Yuan, Yuan ; Li, Xuelong. / Iterative subspace analysis based on feature line distance. In: IEEE Transactions on Image Processing. 2009 ; Vol. 18, No. 4. pp. 903-907.
@article{3afe88cee8b84e6c8eeb7e65b30e0dd2,
title = "Iterative subspace analysis based on feature line distance",
abstract = "Nearest feature line-based subspace analysis is first proposed in this paper. Compared with conventional methods, the newly proposed one brings better generalization performance and incremental analysis. The projection point and feature line distance are expressed as a function of a subspace, which is obtained by minimizing the mean square feature line distance. Moreover, by adopting stochastic approximation rule to minimize the objective function in a gradient manner, the new method can be performed in an incremental mode, which makes it working well upon future data. Experimental results on the FERET face database and the UCI satellite image database demonstrate the effectiveness.",
keywords = "generalization performance, incremental analysis, iterative subspace analysis, mean square feature line distance, nearest feature line, objective function, projection point, stochastic approximation rule",
author = "Yanwei Pang and Yuan Yuan and Xuelong Li",
year = "2009",
month = "4",
doi = "10.1109/TIP.2008.2011167",
language = "English",
volume = "18",
pages = "903--907",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "IEEE",
number = "4",

}

Iterative subspace analysis based on feature line distance. / Pang, Yanwei; Yuan, Yuan; Li, Xuelong.

In: IEEE Transactions on Image Processing, Vol. 18, No. 4, 04.2009, p. 903-907.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Iterative subspace analysis based on feature line distance

AU - Pang, Yanwei

AU - Yuan, Yuan

AU - Li, Xuelong

PY - 2009/4

Y1 - 2009/4

N2 - Nearest feature line-based subspace analysis is first proposed in this paper. Compared with conventional methods, the newly proposed one brings better generalization performance and incremental analysis. The projection point and feature line distance are expressed as a function of a subspace, which is obtained by minimizing the mean square feature line distance. Moreover, by adopting stochastic approximation rule to minimize the objective function in a gradient manner, the new method can be performed in an incremental mode, which makes it working well upon future data. Experimental results on the FERET face database and the UCI satellite image database demonstrate the effectiveness.

AB - Nearest feature line-based subspace analysis is first proposed in this paper. Compared with conventional methods, the newly proposed one brings better generalization performance and incremental analysis. The projection point and feature line distance are expressed as a function of a subspace, which is obtained by minimizing the mean square feature line distance. Moreover, by adopting stochastic approximation rule to minimize the objective function in a gradient manner, the new method can be performed in an incremental mode, which makes it working well upon future data. Experimental results on the FERET face database and the UCI satellite image database demonstrate the effectiveness.

KW - generalization performance

KW - incremental analysis

KW - iterative subspace analysis

KW - mean square feature line distance

KW - nearest feature line

KW - objective function

KW - projection point

KW - stochastic approximation rule

UR - http://www.scopus.com/inward/record.url?scp=63449129600&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4799382

U2 - 10.1109/TIP.2008.2011167

DO - 10.1109/TIP.2008.2011167

M3 - Article

VL - 18

SP - 903

EP - 907

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 4

ER -