Neighbourhood preserving discriminant embedding in face recognition

Pang Ying Han, Beng Jin Teoh, Fazly Salleh Abas

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

In this paper, we present an effective technique on discriminative feature extraction for face recognition. The proposed technique incorporates Graph Embedding and the Fisher's criterion where we call it as Neighbourhood Preserving Discriminant Embedding (NPDE). Utilizing the Graph Embedding criterion, the underlying nonlinear face data structure is revealed as representative and discriminative features for analysis. We employ Neighbourhood Preserving Embedding (NPE) for the purpose. NPE takes into account the restriction that neighbouring points in the high-dimensional space must remain within the same neighbourhood in the low dimension space and be located in a similar relative spatial situation (without changing the local structure of the nearest neighbours of each data point). Furthermore, by taking the advantage of the Fisher's criterion, the discriminating power of NPDE is further boosted. Based on this intuition, NPDE obtains better discriminative capability and experimentally verified in ORL, PIE and FRGC.

Original languageEnglish
Pages (from-to)532-542
Number of pages11
JournalJournal of Visual Communication and Image Representation
Volume20
Issue number8
DOIs
Publication statusPublished - 2009 Nov 1

Fingerprint

Face recognition
Data structures
Feature extraction

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

@article{4d09045672ee431fa9545d12a496a762,
title = "Neighbourhood preserving discriminant embedding in face recognition",
abstract = "In this paper, we present an effective technique on discriminative feature extraction for face recognition. The proposed technique incorporates Graph Embedding and the Fisher's criterion where we call it as Neighbourhood Preserving Discriminant Embedding (NPDE). Utilizing the Graph Embedding criterion, the underlying nonlinear face data structure is revealed as representative and discriminative features for analysis. We employ Neighbourhood Preserving Embedding (NPE) for the purpose. NPE takes into account the restriction that neighbouring points in the high-dimensional space must remain within the same neighbourhood in the low dimension space and be located in a similar relative spatial situation (without changing the local structure of the nearest neighbours of each data point). Furthermore, by taking the advantage of the Fisher's criterion, the discriminating power of NPDE is further boosted. Based on this intuition, NPDE obtains better discriminative capability and experimentally verified in ORL, PIE and FRGC.",
author = "Han, {Pang Ying} and Teoh, {Beng Jin} and Abas, {Fazly Salleh}",
year = "2009",
month = "11",
day = "1",
doi = "10.1016/j.jvcir.2009.08.003",
language = "English",
volume = "20",
pages = "532--542",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",
number = "8",

}

Neighbourhood preserving discriminant embedding in face recognition. / Han, Pang Ying; Teoh, Beng Jin; Abas, Fazly Salleh.

In: Journal of Visual Communication and Image Representation, Vol. 20, No. 8, 01.11.2009, p. 532-542.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neighbourhood preserving discriminant embedding in face recognition

AU - Han, Pang Ying

AU - Teoh, Beng Jin

AU - Abas, Fazly Salleh

PY - 2009/11/1

Y1 - 2009/11/1

N2 - In this paper, we present an effective technique on discriminative feature extraction for face recognition. The proposed technique incorporates Graph Embedding and the Fisher's criterion where we call it as Neighbourhood Preserving Discriminant Embedding (NPDE). Utilizing the Graph Embedding criterion, the underlying nonlinear face data structure is revealed as representative and discriminative features for analysis. We employ Neighbourhood Preserving Embedding (NPE) for the purpose. NPE takes into account the restriction that neighbouring points in the high-dimensional space must remain within the same neighbourhood in the low dimension space and be located in a similar relative spatial situation (without changing the local structure of the nearest neighbours of each data point). Furthermore, by taking the advantage of the Fisher's criterion, the discriminating power of NPDE is further boosted. Based on this intuition, NPDE obtains better discriminative capability and experimentally verified in ORL, PIE and FRGC.

AB - In this paper, we present an effective technique on discriminative feature extraction for face recognition. The proposed technique incorporates Graph Embedding and the Fisher's criterion where we call it as Neighbourhood Preserving Discriminant Embedding (NPDE). Utilizing the Graph Embedding criterion, the underlying nonlinear face data structure is revealed as representative and discriminative features for analysis. We employ Neighbourhood Preserving Embedding (NPE) for the purpose. NPE takes into account the restriction that neighbouring points in the high-dimensional space must remain within the same neighbourhood in the low dimension space and be located in a similar relative spatial situation (without changing the local structure of the nearest neighbours of each data point). Furthermore, by taking the advantage of the Fisher's criterion, the discriminating power of NPDE is further boosted. Based on this intuition, NPDE obtains better discriminative capability and experimentally verified in ORL, PIE and FRGC.

UR - http://www.scopus.com/inward/record.url?scp=70350125913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350125913&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2009.08.003

DO - 10.1016/j.jvcir.2009.08.003

M3 - Article

AN - SCOPUS:70350125913

VL - 20

SP - 532

EP - 542

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

IS - 8

ER -