Face recognition under varying illumination using Mahalanobis self-organizing map

Saleh Aly, Naoyuki Tsuruta, Rin-Ichiro Taniguchi

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

We present an appearance-based method for face recognition and evaluate its robustness against illumination changes. Self-organizing map (SOM) is utilized to transform the high dimensional face image into low dimensional topological space. However, the original learning algorithm of SOM uses Euclidean distance to measure similarity between input and codebook images, which is very sensitive to illumination changes. In this paper, we present Mahalanobis SOM, which uses Mahalanobis distance instead of the original Euclidean distance. The effectiveness of the proposed method is demonstrated by conducting some experiments on Yale B and CMU-PIE face databases.

Original languageEnglish
Pages (from-to)298-301
Number of pages4
JournalArtificial Life and Robotics
Volume13
Issue number1
DOIs
Publication statusPublished - Dec 1 2008

Fingerprint

Self organizing maps
Face recognition
Lighting
Learning
Databases
Learning algorithms
Facial Recognition
Experiments

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence

Cite this

Face recognition under varying illumination using Mahalanobis self-organizing map. / Aly, Saleh; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

In: Artificial Life and Robotics, Vol. 13, No. 1, 01.12.2008, p. 298-301.

Research output: Contribution to journalArticle

@article{2263f5e4b1f44ddf8ab862297bd50e21,
title = "Face recognition under varying illumination using Mahalanobis self-organizing map",
abstract = "We present an appearance-based method for face recognition and evaluate its robustness against illumination changes. Self-organizing map (SOM) is utilized to transform the high dimensional face image into low dimensional topological space. However, the original learning algorithm of SOM uses Euclidean distance to measure similarity between input and codebook images, which is very sensitive to illumination changes. In this paper, we present Mahalanobis SOM, which uses Mahalanobis distance instead of the original Euclidean distance. The effectiveness of the proposed method is demonstrated by conducting some experiments on Yale B and CMU-PIE face databases.",
author = "Saleh Aly and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2008",
month = "12",
day = "1",
doi = "10.1007/s10015-008-0555-z",
language = "English",
volume = "13",
pages = "298--301",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "1",

}

TY - JOUR

T1 - Face recognition under varying illumination using Mahalanobis self-organizing map

AU - Aly, Saleh

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2008/12/1

Y1 - 2008/12/1

N2 - We present an appearance-based method for face recognition and evaluate its robustness against illumination changes. Self-organizing map (SOM) is utilized to transform the high dimensional face image into low dimensional topological space. However, the original learning algorithm of SOM uses Euclidean distance to measure similarity between input and codebook images, which is very sensitive to illumination changes. In this paper, we present Mahalanobis SOM, which uses Mahalanobis distance instead of the original Euclidean distance. The effectiveness of the proposed method is demonstrated by conducting some experiments on Yale B and CMU-PIE face databases.

AB - We present an appearance-based method for face recognition and evaluate its robustness against illumination changes. Self-organizing map (SOM) is utilized to transform the high dimensional face image into low dimensional topological space. However, the original learning algorithm of SOM uses Euclidean distance to measure similarity between input and codebook images, which is very sensitive to illumination changes. In this paper, we present Mahalanobis SOM, which uses Mahalanobis distance instead of the original Euclidean distance. The effectiveness of the proposed method is demonstrated by conducting some experiments on Yale B and CMU-PIE face databases.

UR - http://www.scopus.com/inward/record.url?scp=58049195276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58049195276&partnerID=8YFLogxK

U2 - 10.1007/s10015-008-0555-z

DO - 10.1007/s10015-008-0555-z

M3 - Article

AN - SCOPUS:58049195276

VL - 13

SP - 298

EP - 301

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 1

ER -