A discriminant-based locality preserving embedding in face recognition

Pang Ying Han, Andrew Teoh Beng Jin, Khoh Wee How

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Locally Linear Embedding (LLE) is a popular dimension reduction technique due to its nonlinearity property. However, LLE is restricted to its unsupervised nature and "out-of-sample problem" in which suboptimal to face recognition problem. Hence, we propose a supervised and linear approximation of LLE, known as Neighborhood Preserving Discriminant Embedding (NPDE). Using the class information, NPDE finds an optimal projection so that the ratio of the within-neighborhood scatter and the between-neighborhood scatter is minimized. NPDE signifies the local neighboring geometry that corresponding to the nonlinear underlying data structure in the image space. Based on this intuition, NPDE shows better discriminative capability in face recognition.

Original languageEnglish
Title of host publicationICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics
Pages59-62
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 International Conference on Computer Applications and Industrial Electronics, ICCAIE 2010 - Kuala Lumpur, Malaysia
Duration: 2010 Dec 52010 Dec 7

Publication series

NameICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics

Other

Other2010 International Conference on Computer Applications and Industrial Electronics, ICCAIE 2010
CountryMalaysia
CityKuala Lumpur
Period10/12/510/12/7

Fingerprint

Face recognition
Data structures
Geometry

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Han, P. Y., Jin, A. T. B., & How, K. W. (2010). A discriminant-based locality preserving embedding in face recognition. In ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics (pp. 59-62). [5735047] (ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics). https://doi.org/10.1109/ICCAIE.2010.5735047
Han, Pang Ying ; Jin, Andrew Teoh Beng ; How, Khoh Wee. / A discriminant-based locality preserving embedding in face recognition. ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics. 2010. pp. 59-62 (ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics).
@inproceedings{dda9a2ecc51e4f818cb76d9be660e2af,
title = "A discriminant-based locality preserving embedding in face recognition",
abstract = "Locally Linear Embedding (LLE) is a popular dimension reduction technique due to its nonlinearity property. However, LLE is restricted to its unsupervised nature and {"}out-of-sample problem{"} in which suboptimal to face recognition problem. Hence, we propose a supervised and linear approximation of LLE, known as Neighborhood Preserving Discriminant Embedding (NPDE). Using the class information, NPDE finds an optimal projection so that the ratio of the within-neighborhood scatter and the between-neighborhood scatter is minimized. NPDE signifies the local neighboring geometry that corresponding to the nonlinear underlying data structure in the image space. Based on this intuition, NPDE shows better discriminative capability in face recognition.",
author = "Han, {Pang Ying} and Jin, {Andrew Teoh Beng} and How, {Khoh Wee}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICCAIE.2010.5735047",
language = "English",
isbn = "9781424490554",
series = "ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics",
pages = "59--62",
booktitle = "ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics",

}

Han, PY, Jin, ATB & How, KW 2010, A discriminant-based locality preserving embedding in face recognition. in ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics., 5735047, ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics, pp. 59-62, 2010 International Conference on Computer Applications and Industrial Electronics, ICCAIE 2010, Kuala Lumpur, Malaysia, 10/12/5. https://doi.org/10.1109/ICCAIE.2010.5735047

A discriminant-based locality preserving embedding in face recognition. / Han, Pang Ying; Jin, Andrew Teoh Beng; How, Khoh Wee.

ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics. 2010. p. 59-62 5735047 (ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A discriminant-based locality preserving embedding in face recognition

AU - Han, Pang Ying

AU - Jin, Andrew Teoh Beng

AU - How, Khoh Wee

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Locally Linear Embedding (LLE) is a popular dimension reduction technique due to its nonlinearity property. However, LLE is restricted to its unsupervised nature and "out-of-sample problem" in which suboptimal to face recognition problem. Hence, we propose a supervised and linear approximation of LLE, known as Neighborhood Preserving Discriminant Embedding (NPDE). Using the class information, NPDE finds an optimal projection so that the ratio of the within-neighborhood scatter and the between-neighborhood scatter is minimized. NPDE signifies the local neighboring geometry that corresponding to the nonlinear underlying data structure in the image space. Based on this intuition, NPDE shows better discriminative capability in face recognition.

AB - Locally Linear Embedding (LLE) is a popular dimension reduction technique due to its nonlinearity property. However, LLE is restricted to its unsupervised nature and "out-of-sample problem" in which suboptimal to face recognition problem. Hence, we propose a supervised and linear approximation of LLE, known as Neighborhood Preserving Discriminant Embedding (NPDE). Using the class information, NPDE finds an optimal projection so that the ratio of the within-neighborhood scatter and the between-neighborhood scatter is minimized. NPDE signifies the local neighboring geometry that corresponding to the nonlinear underlying data structure in the image space. Based on this intuition, NPDE shows better discriminative capability in face recognition.

UR - http://www.scopus.com/inward/record.url?scp=79953907314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953907314&partnerID=8YFLogxK

U2 - 10.1109/ICCAIE.2010.5735047

DO - 10.1109/ICCAIE.2010.5735047

M3 - Conference contribution

AN - SCOPUS:79953907314

SN - 9781424490554

T3 - ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics

SP - 59

EP - 62

BT - ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics

ER -

Han PY, Jin ATB, How KW. A discriminant-based locality preserving embedding in face recognition. In ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics. 2010. p. 59-62. 5735047. (ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics). https://doi.org/10.1109/ICCAIE.2010.5735047