Classification using adaptive multiscale retinex and support vector machine for face recognition system

M. M. Sani, Khairul Anuar Ishak, Salina Abdul Samad

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This study presents an efficient face recognition system based on Support Vector Machine. A lighting correction method, i.e., Adaptive multiscale retinex is introduced to reduce various lighting conditions before performing the classification task. The performance of this method is evaluated using the Yale and ORL databases. The recognition rate of the proposed method achieved up to 92% compared to the principal component analysis method with 73.7%.

Original languageEnglish
Pages (from-to)506-511
Number of pages6
JournalJournal of Applied Sciences
Volume10
Issue number6
DOIs
Publication statusPublished - 2010

Fingerprint

Face recognition
Support vector machines
Lighting
Principal component analysis

Keywords

  • Adaptive multiscale retinex
  • Face recognition
  • Principal component analysis
  • Support vector machine

ASJC Scopus subject areas

  • General

Cite this

Classification using adaptive multiscale retinex and support vector machine for face recognition system. / Sani, M. M.; Ishak, Khairul Anuar; Abdul Samad, Salina.

In: Journal of Applied Sciences, Vol. 10, No. 6, 2010, p. 506-511.

Research output: Contribution to journalArticle

@article{69cab9c5ba4040f8acf8d125c879f425,
title = "Classification using adaptive multiscale retinex and support vector machine for face recognition system",
abstract = "This study presents an efficient face recognition system based on Support Vector Machine. A lighting correction method, i.e., Adaptive multiscale retinex is introduced to reduce various lighting conditions before performing the classification task. The performance of this method is evaluated using the Yale and ORL databases. The recognition rate of the proposed method achieved up to 92{\%} compared to the principal component analysis method with 73.7{\%}.",
keywords = "Adaptive multiscale retinex, Face recognition, Principal component analysis, Support vector machine",
author = "Sani, {M. M.} and Ishak, {Khairul Anuar} and {Abdul Samad}, Salina",
year = "2010",
doi = "10.3923/jas.2010.506.511",
language = "English",
volume = "10",
pages = "506--511",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "6",

}

TY - JOUR

T1 - Classification using adaptive multiscale retinex and support vector machine for face recognition system

AU - Sani, M. M.

AU - Ishak, Khairul Anuar

AU - Abdul Samad, Salina

PY - 2010

Y1 - 2010

N2 - This study presents an efficient face recognition system based on Support Vector Machine. A lighting correction method, i.e., Adaptive multiscale retinex is introduced to reduce various lighting conditions before performing the classification task. The performance of this method is evaluated using the Yale and ORL databases. The recognition rate of the proposed method achieved up to 92% compared to the principal component analysis method with 73.7%.

AB - This study presents an efficient face recognition system based on Support Vector Machine. A lighting correction method, i.e., Adaptive multiscale retinex is introduced to reduce various lighting conditions before performing the classification task. The performance of this method is evaluated using the Yale and ORL databases. The recognition rate of the proposed method achieved up to 92% compared to the principal component analysis method with 73.7%.

KW - Adaptive multiscale retinex

KW - Face recognition

KW - Principal component analysis

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=77649134587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649134587&partnerID=8YFLogxK

U2 - 10.3923/jas.2010.506.511

DO - 10.3923/jas.2010.506.511

M3 - Article

AN - SCOPUS:77649134587

VL - 10

SP - 506

EP - 511

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 6

ER -